a verb class only a cognitive semanticist could love

Continuing my walk down dissertation memory lane (walk #1 here), this time I revisit the semantics of barrier verbs (and I remind you that this is largely a cut and paste job from my draft chapter on semantics).

Here is my set of "core" barrier verbs (I'll explain later how I distinguish between core members of a verb class and peripheral members as this was a topic of great interest to me).

ban, bar, barricade, block, deflect, detain, discourage, enjoin, exclude, exempt, guard, hamper, hinder, interrupt, obstruct, protect, pre-empt, prevent, prohibit, restrain, restrict, screen, shield, thwart

Note that neither stop nor keep are in the core set, yet either can easily be coerced into the barrier verb class. A keen spidey sense for semantics might also alert you to the fact that there are two sub-classes within that list: protect versus prevent. Oh, sooo much to discuss there. Too much for now, but yes, semantic madness lies that way.

My linguistics dissertation grew out of work by Len Talmy, so I’ll begin with a brief overview of his work on these verbs. Len wrote a 40 page monograph on this verb class and I may in fact possess the only extant copy. I really should scan that. I'll show in a later post how this semantic description impacts the syntactic construction that barrier verbs often occur in, as well as how the semantics impacts some quirky frequency facts. But for now, on with cognitive semantics!

The class of English barrier verbs are causative object control verbs* which encode the relationships between a goal directed participant (or “agonist” in Len's terms), its goal and a barrier participant (or “antagonist”). Situations involving barriers are more nuanced than simply one thing being in-between two other things. A barrier necessarily impedes the motion of one of the things it is in-between. Barrier situations require motion as well. However, we will see that this motion can be extended metaphorically to intentions and goals if not many other things. If an entity wants to achieve a certain outcome, yet is impeded by some force, this situation can be encoded by a barrier verb. Some examples:

Physical Blocking 

The fence blocked the car from entering the driveway. 

Intentional Exclusion 

The club excluded me from membership. 

Speech Act Pronouncement 

The judge banned journalists from the courtroom. 

Virtual

Spybot protected my computer from a virus.

In the examples above, there is an explicit goal directed agonist (the car, me, journalists, a virus) and a goal (the driveway, membership, the courtroom, my computer). Only in the first sentence is there a physical barrier (the fence). In the other sentences there is an implied barrier (the club’s power to exclude, the judge’s ban, Spybot). But in all cases, the barrier interferes with the goal-directed agonist's ability to achieve its intended outcome.

But interference alone is not enough to properly distinguish a barrier situation from a simple in-the path situation that a verb like place evokes in a sentence like this one:

John placed the table between Chris and the kitchen. 

In this case, to place does not necessarily evoke the notion of interfering with goal-directed motion. One would have to infer (perhaps via Gricean maxims) that Chris wants to enter the kitchen in order derive a barrier interpretation of this sentence. But that notion is not entailed by the verb place, it is at best added via inference. A member of the barrier verb class should entail the notion that the agonist is goal directed (via motion or metaphorical extensions of motion). Therefore, the two end points must have a particular relationship to each another. Namely, one end point participant must be moving towards the other, or have some sort of tendency towards the other end point (this use of tendency is adapted from Talmy).

Talmy assumes a model of barrier dynamics in which there are three salient participants: A GOAL-directed Agonist X, a barrier-forming Antagonist Y, and a GOAL Z. Figure 1 (Talmy loves figures) represents this state of affairs where the arrow represents the X participant’s tendency towards the Z participant.

Talmy also recognizes the potential for the inclusion of a SOURCE entity as well (“an object at which the Agonist begins its path” (unpublished manuscript: 2), but it is only these three salient X, Y, Z entities which form the necessary basic structure of barrier dynamics.

Note that the inclusion of a GOAL distinguishes this set of situations from simple impeded motion, lexicalized in such English verbs as “stop”:

• I stopped the lawnmower.
• The judge banned journalists.

In the first case, the lawnmower is not encoded with any inherent GOAL by virtue of the meaning of stop. This could simply mean that the lawnmower was turned off. Note, however that adding a complement with the preposition from adds the notion of GOAL:

• I stopped the lawnmower from destroying the flowers.

Above,  the verb ban encodes journalists with an inherent GOAL (presumably the judge’s courtroom as it would be pragmatically odd for a judge to ban journalists from her kitchen). Is this inherent tendency towards a goal a presupposition or invited inference or semantic entailment? Those arguments must wait for later.

What's crucial is that this tendency toward a GOAL is part of what constitutes the barrier situation and hence acts as a distinguishing feature which separates these verbs from other stopped-motion verbs like stop.

It is important to recognize that this set of situations is not just a possible set of events in the world but is actually lexicalized in certain English verbs, forming a natural class (there are cognate classes in Dutch and German and probably other languages). Identifying the properties of the verbs in this class (particularly with respect to the prepositions from and against) will require empirical, corpus based methods that will be the subject of later posts.

But what will really blow your mind is when I post about the difference betwen these two sentences:

Chris kept the dogs barking.

Chris kept the dogs from barking.

Chew on that for awhile.

*Maybe. I recognize that calling a verb a causative object control verb requires you to believe in such things as causative object control verbs, and some do not. There's really no escaping at least some theoretical stipulations.

On Ennui and Verb Classification Methodologies

Linguists and NLPers alike love word classes, especially verb classes. But linguistic categories are are tricky little buggers. They drove me to a deep ennui which led me out of academia and into industry.

Nonetheless, I occasionally retrace my old steps. Recently, I stumbled across an old chapter from my failed dissertation on verb classes and wondered if this little table of mine still holds water:

Here was the motivation (this is a cut and paste job from a draft chapter, largely unedited. Anyone already familiar with standard verb classification can easily skim away): The general goal of any verb classification scheme is to group verbs into sets based on similar properties, either semantic or syntactic. For linguists, the value of these classifications comes from trying to understand how the human language system naturally categorizes verbs within the mental lexicon (the value may be quite different for NLPers). One assumes that the human language system includes some categorical association between verbs within the mental lexicon and one attempts to construct a class of verbs that is consistent with those mental lexicon associations.

Verbs can be categorized into groups based on their semantic similarity. For example, the verbs hit, punch, kick, smack, slap could all be categorized as verbs of HITTING. They could also be grouped based on constructions. For example, verbs like give and send occur in both the ditransitive and double object constructions:
Ditransitive

Chris gave the box to Willy.
Chris sent the box to Willy.

Double Object

Chris gave Willy the box.
Chris sent Willy the box.

Verb classes have long been a central part of linguistics research. However, any set of naturally occurring objects can allow different sub-groups to be created using different criteria or features. The unfortunate truth is that we don’t really know how the mental lexicon is organized (this is not to say that patterns of relations have not been found using, say, priming experiments, or language acquisition, or fMRI. They have. But the big picture of mental lexicon organization remains fuzzy, if not opaque). Therefore, all verb classifications are speculative and all verb classification methodologies are experimental. Two key challenges face the verb classification enterprise:

1. Identify the natural characteristics of each class (e.g., defining the frame)
2. Identify the verbs which invoke the frame (e.g., which verbs are members of the class)

But how do we overcome these two challenges? There is, as yet, no standard method for doing either. Most verb classification projects to date have employed some combination of empirical corpus data collection, automatic induction (e.g., k-means clustering), psycholinguistic judgment tasks or old fashioned intuition. Nonetheless, in recent years there have emerged certain best practices which appear to be evolving into a de facto standard.

This emerging de facto standard includes a mixture of intuitive reasoning (about verbs, their meaning, and their relationships to each other) and corpus analysis (e.g., frequencies, collocations). Below is a table detailing methods of verb classification and some of the major researchers associated with the methods:

But how do we know if our speculations about a verb class are "correct" (in the sense that a proposed class should be consistent with a class assumed to exist in the mental lexicon)? The quick answer is that we don’t. Without a better understanding of the mental lexicon, we are left to defend our classes based on our methods only: proposed verb class A is good to the extent that it was constructed using sound methods (a somewhat circular predicament). We also have cross-validation testing methods available. If my class A contains most of the same verbs that your class B contains (using different methods of constructing the classes) this suggests that we have both identified a class that is consistent with a natural grouping. Finally, via consensus, a certain classification can emerge as the most respected, quasi-gold standard classification and further attempts to create classes can be measured by their consistency with that gold standard.

The closest thing to a gold standard for English verb classes is the Berkeley FrameNet project. FrameNet is perhaps the most comprehensive attempt to hand-create a verb classification scheme that is consistent with natural, cognitively salient verb classes. It is based on painstaking annotation of naturally occurring sentences containing target words.

But even FrameNet is ripe for criticism. It's not good at distinguishing exemplar members of a verb class from coerced members, save by arbitrary designation.

For example, I was working on a class of verbs evoking barrier events like prevent, ban, protect. What was curious in my research was how some verbs had a strong statistical correlation with the semantics of the class (like prevent and protect), yet there were others that clearly appeared in the proper semantic and syntactic environments evoking barriers, but were not, by default, verbs of barring. For example, stop. The verb stop by itself does not evoke the existence of a barrier. For example, "Chris stopped singing", or "It stopped raining." Neither of those two events involve a barrier to the singing or raining. Yet in "Chris stopped Willy from opening the door" there is now a clear barrier meaning evoked (yes yes, the from is crucial. I have a a whole chapter on that. What will really blow your mind is when you realize that from CANNOT be a preposition in this case...).

The process of coercing verbs into a new verb class with new meaning was a central part of my dissertation. Damned interesting stuff. I found some really weird examples too. For example I found a sentence like "Chris joked Willie into going to the movie with us", meaning Chris used the act of joking to convince Willie to do something he otherwise would not have done.

Linguistic Curiosities in 'Elysium'

Matt Damon's latest hit movie Elysium has a few linguistic oddities worth pointing out. The film takes place in a dystopian future set in 2154.

• Jodie Foster's weird accent. She speaks French occasionally in the movie, but when she speaks English, she affects a weird accent that is un-placeable, inconsistent, and off-putting. A good director needs to tell a star like Foster that it's just not working, go back to your real voice.


• Matt Damon's inexplicable bilingualism. His character "Max" is shown growing up speaking Spanish, surrounded by Spanish speakers. The boy inexplicably starts speaking English in one scene. When we meet the adult Max, his English is fluent. One could make the argument that he learned English somewhere in the missing years the movie doesn't show. Here's the thing, we get to hear all of his friends speaking English too, and they all speak with Spanish accents! Max is the only one who manages to grow up in that Spanish dominant culture and yet speak flawless English.


• Speech synthesis straight out of 1998. Damon has an early scene with a robo-parole officer which speaks with a stilted, halting robo-voice that reminded me of speech synthesis that's already ten years out-of-date. This is the same movie that depicts medical science as being so advanced, a machine can diagnose and cure any disease in seconds. Harumph...


• Horrible dialogue dubbing (non-linguistic, but worth pointing out.). Particularly for Jodie Foster, the sound dubbing was awful, destroying any suspension of disbelief I managed to retain in spite of the many ridiculous moments in the film. Not gonna win any sound editing awards anytime soon.

Dystopian futures are a peculiar genre in film making. From cheap Aussie films like Mad Max to slick Hollywood blockbusters like Blade Runner, they've been a staple of film makers who want to make a social statement while also giving the audience a fun romp. But, for a dystopian film to really work it needs to care about creating believability in at least three broad areas: 1) visual world 2) social world, and 3) plot. Sadly, most movies devote all their time to 1 and precious little to 2 and 3. Elysium is clearly one of the many that put all their budget into look and feel and none into the story.

While Neill Blomkamp managed to create a visually beautiful world, the story is pure shit. It's the worst kind of liberal stereotype where every rich person is an evil sociopath and every poor person is a good hearted victim. It's too bad because there is a core of truth to the movie. There really is a tremendous wealth gap and there really are tragic inequalities, but this movie uses these facts as little more than a cheap backdrop to a thin beat 'em up thriller while pretending to be a socially conscious movie.

But here's the thing: There are no lessons in this movie. You won't gain a deeper understanding of anything. You won't have an "a hah" moment. It's Fox News for liberals, and it's equally as patronizing and empty. It's clear that Blomkamp put all his energy into the look of the film, and none into the story. There is tremendous nuance and detail in every item of clothing and every object, but the social structure is barely a cartoon and the plot is wafer thin (crucially depending on a series of coincidences like bad action films so often do). Ultimately, it was not really worth it. I'd like my $7 matinee ticket back, please.

in the dark heart of a language model lies madness....

This is the second in a series of post detailing experiments with the Java Graphical Authorship Attribution Program. The first post is here.

In my first run (seen above), I asked JGAAP to normalize for white space, strip punctuation, turn everything into lowercase. Then I had it run a Naive Bayes classifier on the top 50 tri-grams from the three known authors (Shakespeare, Marlowe, Bacon) and one unknown author (Shakespeare's sonnets).

Based on that sample, JGAAP came to the conclusion that Francis Bacon wrote the sonnets. We know that because it lists its guesses in order from best to worst in the left window in the above image. Bacon is on top. This alone is cause to start tinkering with the model, but the results didn't look as flat weird until I looked at the image again today. It lists the probability that the sonnets were written by Bacon as 1. A probability of 1 typically means absolute certainty. So this model, given the top 50 trigrams, is absolutely certain that Francis Bacon wrote those sonnets ... Bullshit. A probabilistic model is never absolutely certain of anything. That's what makes it probabilistic, right?

So where's the bug? Turns out, it might have been poor data management on my part. I didn't bother to sample in any kind of fair and reasonable way. Here are my corpora:

Known Authors

• Bacon - (2 works) - 950 KB
• Marlowe (Works vol 3) - 429 KB
• Shakespeare (all plays) - 4.4 MB

Unknown Author

• (Sonnets) - 113 KB

Clearly, I provided a much larger Shakespeare data set than any of the others. However, keep in mind that JGAAP only used the 50 most common tri-grams from any of these corpora (if I understand their Event Culling tool properly). Is the disparity in corpora size relevant if I'm also sampling just the top 50 tri-grams? Just how different would those tri-grams be if the corpora were equivalent? Let's find out.

The Infinite Madness of Language Models 
As far as I can tell, the current version does not have any obvious way of turning on error reporting logs (though I suspect that is possible, if one had the source code). It also offers no way of printing the features it's using. Id' love to see a list of those top 50 tri-grams for each author. But as of right now, it does not appear to support that. I'll add that to my enhancement requests. However, JGAAP is fast enough to simply run several trial-and-error runs in order to compare output. My goals are 1) get JGAAP to guess Shakespeare as the unknown author with a high degree of certainty and 2) try to figure out why it gave such a high confidence score to Bacon during round one.

Here are the results of several follow up experiments. Mostly, I want to tune the language model - in the parlance of JGAAP, Event Drivers (linguistic features) + Event Culling (sampling) = a language model (unless I'm misunderstanding something).

Round 2: Same specifications as Round one. I used the all of the same corpora, except I replaced Shakespeare with a sample of about 500 KB to bring it in line with the others. Then I repeated the analysis using all the same parameters. This time ... drum roll ... Bacon still wins in a landslide. JGAAP remains absolutely confident that Bacon wrote those sonnets.

Round 3: Okay. Let's expand the set of tri-grams. Same everything else as Round 2, but now I'll use the top 100 tri-grams.

D'oh! Well, it's less confident that Marlowe is involved (drunk bastard).

Round 4: For good measure. Let's expand the set of tri-grams. Same everything else as Rounds 2 and 3, but now I'll use the top 200 tri-grams.

Dammit!!

Okay, it appears that adding more tri-grams alone gives us nothing. I feel confident dropping back down to 100. Now, I'll add one simple feature - Words (I assume this is a frequency list; again, the Event Culling will choose just the top 100 most frequent words, as well as the top 100 tri-grams, if I'm understanding this right).

We have a winner! The top score above shows that for Words, Shakespeare finally wins (though he still loses on Ngrams, the second highlighted score). As a comparison, I threw in another feature, Rare Words.

No help. My interpretation of these results is that the feature "Words" is the best predictor of Shakespearean authorship (given this set of competing authors with these tiny corpora).

But this is a stacked-deck experiment. I know perfectly well that the "Unknown Author" is Shakespeare. I'm just playing with linguistic features until I get the result I want. The actual problem of determining unknown authorship requires far more sophisticated work than what I did here (again, read Juola's detailed explanation of what he and his team did to out J.K. Rowling).

Nonetheless, I could imagine not sleeping for several days just playing with the different combinations of features to produce different language models just to see how they move the results (mind you, I didn't play with the classifier either, which adds its own dimension of playfulness).

Herein lies the value of JGAAP. More than any other tool I have personally seen, JGAAP gives the average person the easy-to-use platform to splash around and play with language in an NLP environment. When thinking about my first two experiences with JGAAP, the most salient word that jumps out at me is FUN! It's just plain fun to play around. It's fast and simple and fun. I can't say that about R, or Python, or Octave. All three of those are very powerful tool sets, but they are not fun. JGAAP is fun. It's a playground for linguists. Let me note that I beta tested a MOOC for WEKA last March and was very impressed with their interface as well (though I think JGAAP does a better job of making language modeling easy ... and that's the fun part for linguists anyway).

I am reminded of what several Twitter friends have said to me when I say that I'm a cognitive linguist: "Really! I never would have known by your Twitter feed." That's a wake up call for me. I have been involved in NLP since roughly 2000, but my passion is definitely the blood and guts of language and linguistics. JGAAP appeals to that old linguistics fire in my belly. It make me want to play with language again.

Harry Potter Wrote Shakespeare's Sonnets!!!

No, of course not. That's silly.

But the recent outing of J.K. Rowling as the one true author of a crime novel published under a pseudonym was interesting not least because the software used to out her is freely available and, as it turns out, shockingly easy to use (too easy?*). You can read how Peter Millican and Patrick Juola uncovered the truth of Rowling's authorship in various places, such as:

Rowling and "Galbraith": an authorial analysis (Language Log)

You enjoy catching up to the rest of us who have actually been awake the last week or so. What I want to do is play. Much like I did with IBM's Text Analysis platform, I'm going to perform a few linguistic experiments with JGAAP over the next few weeks. The software Millican and Juola used is called the Java Graphical Authorship Attribution Program, or JGAAP. It's freely downloadable and user friendly.

I downloaded the software and opened the GUI in seconds (though the initial download site was spurious, an email to the developers quickly resolved that).

I'm running this on a modest laptop: Lenovo X100e with AMD 1.6GHz processor, 2.75 usable GB RAM, 32-bit Windows 7 OS.

First, I loaded three known authors:

1. Shakespeare - a single text file with all plays.
2. Christopher Marlowe - a single file from Gutenberg with most works.
3. Francis Bacon - two text files: The Advancement of Learning and Book of Essays.

Then I loaded one "unknown author" for comparison (a single file of all Shakespeare's sonnets).

JGAAP provides very easy methods of adding all kinds of linguistic and document features to check and classifiers to use to categorize them. On my first try I chose 3 or 4 Canonicizers (normalizing the text for things like white space, punctuation, capitalization), 5 or 6 Event Drivers (ngrams, word length, POS, etc), 1 Event Culling (Most Common = 50, which I assume means to only care about the 50 most common tri-grams, word lengths, POSs), and WEKA Naive Bayes. Sadly, this failed after about 2 minutes and gave me an error message pointing me to log files. I couldn't find any log files, but I suspect I need to muck with my memory allocation for this heavy of processing.

Second, I wised up and I chose sparsely: 3 Canonicizers [normalize white space, strip punctuation, unify case], 1 event driver = Word Ngram-3, 1 Event Culling = most common events - 50, analysis method WEKA Naive Bayes Classifie).

This successfully produced results in about 2-3 minutes, though it thinks Francis Bacon wrote Shakespeare's sonnets (and really, who am I to disagree?).

This was but the first volley in a long battle, to be sure. But initial results are very promising. Dare I wonder if we are nearing that threshold moment when serious text analysis will require as many engineers as driving to the store requires mechanics?

*One could be forgiven for fearing that by hiding the serious intricacies of the mathematical classifiers and the more-art-than-science language models, JGAAP has put a weapon into the hands of children. I disagree (though not that strongly). My feeling is that JGAAP is to NLP what SPSS is to statistics. Serious statisticians probably just gasped in horror at the implications. But then again, serious drivers gasp in horror at the very idea of an automatic transmission. Technology made to fit the hands of the average is not as bad a thing as technical experts typically fear.

Let me pre-respond to one possible analogy: this is particularly salient a fear given the recent dust-up over bad neuroscience reporting (for example, read this). This is beside the point in that bad science journalism is its own special illness. It doesn't bear on the health of the underlying science.

Stuff to do in DC

A Twitter friend is coming to Washington DC for July and has blegged for local dives.  While there are guides aplenty for things to do in DC, there's nothing that beats a local's recommendation. So, for what it's worth, here's my list of what people coming to DC aught to take advantage of (admittedly heavy on NW).

But before I give you my recommendations, pleeeze deeer gawd!!!! Stand to the right, walk to the left on the frikkin escalators!!!

Okay...

Dive Bars

• The Raven Grill: Tiny bar. You have to squeeze your way in. I watched one of the 2004 Bush v Kerry presidential debates here on a small black and white TV mounted in the corner. It was a partisan crowd, to say the least. (Mt. Pleasant, Columbia Heights green/yellow line).
• Wonderland Ballroom: Isolated location. I thought I was lost the first time I tried to find it. Weird to be next to a school. But it's pretty awesome. Upstairs dance floor. (Columbia Heights green/yellow line).
• Galaxy Hut: Honestly, I thought this place was a hipster dance club the first 100 times I walked by it and never gave it a second glance until someone told me it was for serious beer drinkers only. This book should not be judged by its cover. (Clarendon, orange line).
• Stan's Restaurant: Lived near this place for a year and never gave it a second glance because it's buried in a basement. Turns out, it's a surprisingly awesome and friendly establishment. They pour their drinks like everyone is Hunter Thompson. Gawd help you if you ain't.(Thomas Circle, McPherson Square orange/blue line).

Not dives but worth the time

• DC9: Small, but very fun live music venue. Most things DC run through DC9. (U Street, U street metro green/yellow line).
• Bistro d'OC : Small French restaurant. Excellent food. The cheesy, touristy neighborhood grew up around them, don't blame them. They were there first. (Metro Center, orange, blue, red lines).
• Black Cat: Like DC9, most things DC run through Black Cat (U Street, U street metro green/yellow line).
• Busboys and Poets: The godfather of DC's soul. If you visit DC and fail to make your pilgrimage to Busboys and Poets, well, that's your choice, ain't it? (U Street, U street metro green/yellow line).
• Twins Jazz: How could you not love a jazz club opened by Ethiopian twins. C'mon, man, This is what defines local flare. (U Street, U street metro green/yellow line).
• ChurchKey : Beer lover's paradise. Temperature controlled down to the degree. A host of cask conditioned beers on tap. This is where beer poseurs go to die. Serious beer drinkers only, please. (Thomas Circle, McPherson Square orange/blue line).
• Woolly Mammoth Theater (Archives metro, green/yellow line).
• Warehouse Theater (Mt Vernon Square metro, green/yellow line).
• E Street Cinema: What? A clean, well kept indie cinema in an easily accessible area? Who woulda thought?  (Metro Center, orange, blue, red lines).
• West End Cinema: More indie cred than E Street, but also small, cramped theaters, kinda boring location, and they play the movies from a frikkin DVD. Meh. (Foggy Bottom, orange/blue lines).
• Hike Rock Creek Park. Runs North-South along the district. There are some remarkably remote-seeming locations within this park, even though you're always dead center of DC. NYC's Central park ain't got that.
• Arena Stage (Waterfront Metro, green line).
• Capital Fringe Festival: I have always believed in the value of creativity for creativity's sake. We ain't ants. (various locations).
• Eat at a "gourmet" DC Food truck. Food is awesome. Mobile food is awesome. Why should tacos own the food truck market? Do you hear me, Austin? 

General Recommendations

Walk
I'm a fan of seeing a city by the soles of your shoes and DC is a particularly walkable city. With smart phone maps and recommendation apps, DC becomes a good city to discover by foot. A comfortable pair of walking shoes are your best friend.

Capital Bike Share
For longer stays, DC's bike share program is great. They have daily, weekly, monthly and annual plans.

The Touristy Stuff
There's nothing wrong with taking advantage of touristy accommodations like bus tours because they hit the obvious highlights quickly and efficiently. Particularly with respect to The National Mall, most people have no clue just how big it is. Walking the monuments and Smithsonians is itself a monumental task that is damned tiring, especially in the hot, humid DC summer.

For the touristy stuff I highly recommend the following:

1. The National Zoo (Woodley Park red line).
2. The Lincoln Memorial (Foggy Bottom, orange/blue line).
3. The Hirshhorn Museum and Sculpture Garden (on The Mall).
4. Lunch at the cafe in the National Museum of the American Indian (on The Mall).
5. The White House (yes yes, it really is that small).
6. Wander around the Botanic Garden (on The Mall).
7. You'll wait forever to get to the top of The Washington Monument; instead, go to the tower at The Old Post Office just a few blocks away. Quick, easy, and almost as great of a view.
8. The interior courtyard at The Portrait Museum (Chinatown, green/yellow line).

Things to avoid

• The Spy Museum - blah, always a line, expensive, cheesy and not worth it.
• The Air and Space Museum - always packed and frankly, outdated. The phone in your hand has more impressive technology than that on display in this mothball museum.
• Five Guys Burgers - this chain has pulled a perfect Keyser Söze. The only thing they ever did was con the world into believing they made food worth eating. They never bothered to actually make food worth eating. It's McDonalds with super sized salt. A coronary waiting to happen. Eat at a food truck, you won't be disappointing.
• Georgetown. Basically, douchebag central.  Maybe 30 years ago there was some haute culture vibe worth observing, but now it's little more than corporate United Colors of Benetton, reality-show-cupcakes, polo-shirt-collar-flipped-up douchebag central. And I swear, if one more spandex-clad person goes jogging along the narrow sidewalks of M street shoving people out of their way as if their weekend jog somehow holds moral precedent over everyone else, Imma call a drone strike on their ass.

Personal Favorites
Everybody wants to know some local flare, the inside scoop. Here are some of my personal favorites (dictated somewhat by where I live). Some are well within walking distance of the touristy stuff

1. Snack at Teaism, Penn Quarter (8th street NW, near the White House).
2. Walk Roosevelt Island (Rosslyn Metro, orange/blue line).
3. Take the tourist boat from Georgetown to Old Town in the evening (metro back).
4. Ride a bike along the The Capital Crescent Trail that takes you from Georgetown to Bethesda (maybe 12 miles or so of relatively flat easy cycling). Have lunch, bike back. 
5. Eat Ethiopian food. (U Street, U street metro green/yellow line).
6. Sunday Brunch ... anywhere. DC is brunch crazy.
7. Shoot pool at Bedrock Billiards (Adam's Morgan).
8. Coffee and reading at Northside Social (Clarendon Metro, orange line).
9. Artisphere (Rosslyn Metro, orange/blue line) .
10. Join my Books and Banter book club.
11. Bike the Anacostia Riverwalk Trail. 
12. Lunch at Whole Foods, P Street. People watch. (Thomas Circle, McPherson Square orange/blue line).
13. Listen to Kojo Nnamdi noon to 2 on WAMU.
14. Smoke a cigar at Jay's Saloon (Clarendon, orange line.Talk about dives!).
15. Sushi at Sushi Taro, 17th and P NW.
16. Falafal at Amsterdam Falafal (Adams Morgan).
17. Blues Alley (one of the few Georgetown places I go to regularly).
18. Buy a copy of Street Sense for a dollar (from a badged vendor).

Leave DC
Plenty of stuff in the neighborhood.

• Train to Baltimore, Little Italy and Fells Point (HonFest in June, but that's over).
• Drive to Herndon for Indian food (Angeethi is one of my favs).
• Bus to Eden Center for Vietnamese food, Falls Church.
• Metro to The State Theatre for live music (East Falls Church metro, orange line, you can also bike in on the WOandD).
• WOandD Trail, take a 50 mile bicycle ride into Virginia and back, 100 mile round trip).
• Play the Sunday poker tournament at Hollywood Casino in West Virginia (1 hour drive).

Blame the linguists!

Pullum has let me down. His latest NLP lament isn’t nearly as enraging or baffling as his previous posts.

I basically agree with his points about statistical machine translation. I even agree with his overall point that contemporary NLP is mostly focused on building commercial tools, not on mimicking human language processes.

But Pullum offers no way forward. Even if you agree 100% with everything he says, re-read all four of his NLP laments (one, two, three, four) and ask yourself: What’s his solution? His plan? His proposal? His suggestion? His hint? He offers none.

I suspect one reason he offers no way forward is because he mis-analyzes the cause. He blames commercial products for distracting researchers from doing *real* NLP.

His basic complaint is that engineers haven’t built real NLP tools yet because they haven’t used real linguistics. This is like complaining that drug companies haven’t cured Alzheimer’s yet because they haven’t used real neuroscience. Uh, nope. That’s not what’s holding them back. There is a deep lack of understanding about how the brain works and that’s a hill that’s yet to be climbed. Doctors are trying to understand it, but they’re just not there yet.

He never addresses the fact that linguists have failed to provide engineers with a viable blueprint for *real* machine translation, or *real* speech recognition, or *real Q&A. Sorry, Geoff. The main thing discouraging the development of *real* NLP is the failure of linguists, not engineers. Linguists are trying to understand language, but they’re just not there yet.

Pullum and Huddleston compiled a comprehensive grammar of the English language. Does Pullum believe that work is sufficient to construct a computational grammar of English? One that would allow for question answering of the sort he yearns for? The results would surely be peppered with at least as many howlers as Google translate. If his own comprehensive grammar of English is insufficient for NLP, then what does he expect engineers to use to build *real* NLP?

It’s not that I don’t like the idea of rule-based NLP. I bloody love it. But Pullum acts like it doesn’t exist, when in fact, it does. Lingo Grammar is a good example. But even that project is not commercially viable.

One annoying side point worth repeating: Pullum repeatedly leads his reader towards a false conclusion: that Google is representative of NLP. Yes, Google is heavily invested in statistical machine translation, but there exist syntax-based translation tools that use tree structures, dependencies, known constructions, and yes even semantics. Pullum fails to tell his readers about this. In fact, most contemporary MT systems tend to be hybrids, combining some rule-based approaches with statistical approaches.

In Pullum's defense (sort of), I like big re-thinks (MIT tried a big AI re-think, though it's not clear what has come of it). But Pullum hasn't engaged in big-re-thinking. He makes zero proposals. Zero.

One bit of fisking I will add:

Machine translation is the unclimbed Everest of computational linguistics. It calls for syntactic and semantic analysis of the source language, mapping source-language meanings to target-language meanings, and generating acceptable output from the latter. If computational linguists could do all those things, they could hang up the “mission accomplished” banner.

How does translation work in the brain, Geoff? It’s not so clear exactly how bilinguals perform syntactic and semantic analysis of the source language, map source-language meanings to target-language meanings, and generate acceptable output. Contemporary psycholinguistics cannot state with a high degree of certainty whether or not bilinguals store words in their two languages together or separately, let alone explicate the path Geoff sketches out. Even if it is true that bilinguals translate the way Pullum suggests, it is also true that linguists cannot currently provide a viable blueprint of this process such that engineers could use it to build a *real* NLP machine translation system.

And that's what I have to say about that.