17 February 2010

Senses versus metaphors

I come from a tradition of not really believing in word senses. I fondly remember a talk Ed Hovy gave when I was a grad student. He listed the following example sentences and asked each audience member to group them in to senses:

  1. John drove his car to work.
  2. We dove to the university every morning.
  3. She drove me to school every day.
  4. He drives me crazy.
  5. She is driven by her passion.
  6. He drove the enemy back.
  7. She finally drove him to change jobs.
  8. He drove a nail into the wall.
  9. Bill drove the ball far out into the field.
  10. My students are driving away at ACL papers.
  11. What are you driving at?
  12. My new truck drives well.
  13. He drives a taxi in New York.
  14. The car drove around the corner.
  15. The farmer drove the cows into the barn.
  16. We drive the turnpike to work.
  17. Sally drove a golf ball clear across the green.
  18. Mary drove the baseball with the bat.
  19. We drove a tunnel through the hill.
  20. The steam drives the engine in the train.
  21. We drove the forest looking for game.
  22. Joe drove the game from their hiding holes.
Most people in the audience came up with 5 or 6 senses. One came up with two (basically the physical versus mental distinction). According to wordnet, each of these is a separate sense. (And this is only for the verb form!) A common "mistake" people made was to group 1, 2, 3, 13 and 14, all of which seem to have to do with driving cars. The key distinction is that 1 expresses the operation of the vehicle, 2 expresses being transported, 3 expresses being caused to move and 13 expresses driving for a job. You can read the full WordNet descriptions if you don't believe me.

Now, the point of this isn't to try to argue that WordNet is wacky in any way. The people who put it together really know what they're talking about. After all, these senses are all really different, in the sense there really is a deep interprative difference between 1, 2, 3 and 13. It's just sufficiently subtle that unless it's pointed out to you, it's not obvious. There's been a lot of work recently from Ed and others on "consolidating" senses in the OntoNotes project: in fact, they have exactly the same example (how convenient) where they've grouped the verb drive in to seven senses, rather than 22. These are:
  1. operating or traveling via a vehicle (WN 1, 2, 3, 12, 13, 14, 16)
  2. force to a position or stance (WN 4, 6, 7, 8, 15, 22)
  3. exert energy on behalf of something (WN 5, 10)
  4. cause object to move rapidly by striking it (WN 9, 17, 18)
  5. a directed course of conversation (WN 11)
  6. excavate horizontally, as in mining (WN 19)
  7. cause to function or operate (WN 20)
Now, again, I'm not here to argue that these are better or worse or anything in comparison to WordNet.

The point is that there are (at least) two ways of explaining the wide senses of a word like "drive." One is through senses and this is the typical approach, at least in NLP land. The other is metaphor (and yes, that is a different Mark Johnson). I'm not going to go so far as to claim that everything is a metaphor, but I do think it provides an alternative perspective on this issue. And IMO, alternative perspectives, if plausible, are always worth looking at.

Let's take a really simple "off the top of my head" example based on "drive." Let's unrepentantly claim that there is exactly one sense of drive. Which one? It seems like the most reasonable is probably OntoNotes' sense 2; Merriam-Webster claims that drive derives from Old-High-German "triban" which, from what I can tell in about a five minute search, has more to do with driving cattle than anything else. (But even if I'm wrong, this is just a silly example.)
  1. Obviously we don't drive cars like we drive cattle. For one, we're actually inside the cars. But the whole point of driving cattle is to get them to go somewhere. If we think of cars as metaphorical cattle, then by operating them, we are "driving" them (in the drive-car sense).
  2. These are mostly literal. However, for "drive a nail", we need to think of the nail as like a cow that we're trying to get into a pen (the wall).
  3. This is, I think, the most clear metaphorical usage. "He is driving away at his thesis" really means that he's trying to get his thesis to go somewhere (where == to completion).
  4. Driving balls is like driving cattle, except you have to work harder to do it because they aren't self-propelled. This is somewhat like driving nails.
  5. "What are you driving at" is analogous to driving-at-thesis to me.
  6. "Drive a tunnel through the mountain" is less clear to me. But it's also not a sense of this word that I think I have ever used or would ever use. So I can't quite figure it out.
  7. "Steam drives an engine" is sort of a double metaphor. Engine is standing in for cow and steam is standing in for cowboy. But otherwise it's basically the same as driving cattle.
Maybe this isn't the greatest example, but hopefully at least it's a bit thought-worthy. (And yes, I know I'm departing from Lakoff... in a Lakoff style, there's always a concrete thing and a non-concrete thing in the Lakoff setup from what I understand.)

This reminds me of the annoying thing my comrades and I used to do as children. "I come from a tradition..." Yields "You literally come from a tradition?" (No, I was educated in such a tradition.... although even that you could ask whether I was really inside a tradition.) "A talk Ed Hovy gave..." Yields "Ed literally gave a talk?" (No, he spoke to an audience.) "I drove the golf ball across the field" Yields "You got in the golf ball and drove it across the field?" Sigh. Kids are annoying.

Why should I care which analysis I use (senses or metaphor)? I'm not sure. It's very rare that I actually feel like I'm being seriously hurt by the word sense issue, and it seems that if you want to use sense to do a real task like translation, you have to depart from human-constructed sense inventories anyway.

But I can imagine a system roughly like the following. First, find the verb and it's frame and true literal meaning (maybe it actually does have more than one). This verb frame will impose some restrictions on its arguments (for instance, drive might say that both the agent and theme have to be animate). If you encounter something where this is not true (eg., a "car" as a theme or "passion" as an agent), you know that this must be a metaphorical usage. At this point, you have to deduce what it must mean. That is, if we have some semantics associated with the literal interpretation, we have to figure out how to munge it to work in the metaphorical case. For instance, for drive, we might say that the semantics are roughly "E = theme moves & E' = theme executes E & agent causes E'" If the patient cannot actually execute things (it's a nail), then we have to figure that something else (eg., in this case, the agent) did the actual executing. Etc.

So it seems like the options are: come up with semantics and frames for every sense (this is what's done, eg., in VerbNet). Or, have a single (or small number) of semantics and frames and have some generic rules (hopefully generic!) for how to derive metaphorical uses from them.

9 comments:

Unknown said...

Steven Pinker has a related discussion in his "Stuff of Thought". He shows a nice trick to differentiate the types of meanings hidden behind the verbs. Each "similar" meaning admits the same types of sentence construction, while different meanings clash in the way possible sentence constructions "are allowed". These cut across verb boundaries, so when you have the verb "to drive" meaning different things in separate sentences, changing both sentence structures might help clarify the semantic difference.

For example, the meaning of "change of possession" admits the two following constructions (in the sense of both sounding okay): "She gave him a nice watch" and "She gave a nice watch to him". However, while "she gave him a headache" sounds fine, "she gave a headache to him" sounds really strange.

In the same sense, "He drove the car to Chicago" does not like being switched to "He drove Chicago the car", suggesting (obviously in this case) that the meaning here is not a change of possession. Really cool stuff!

hal said...

Carlos: Good points. Though I'm not sure I totally agree (with Pinker, that is). It's easy to get mixed up when the nouns themselves imply things... For instance "I drove the car over the bridge" versus "I drove the battleship over the bridge"... it's not the driving that presenting a conflict here. This is more subtle but I would argue the same in the last example of driving the car to Chicago -- here, I think it's actually the preposition that's different. For instance, in Japanese, the two "to"s would be translated differently for "Drove the car to Chicago" and "Gave the gift to Mary".... or in Latin, they'd be inflected differently (if I remember from high school). I think this is a good game to play, but I think you have to be very careful when you do so to make sure that it's actually the verb that's not selecting properly, rather than something else in the sentence.

Bob Carpenter said...

A standard linguistic test of ambiguity (e.g. different senses) versus vagueness (e.g. metaphor) would be coordination of arguments. Consider:

1) John drove a car and a golfball.

The infelicity (linguist speak for "sounds funny") of the coordination leads to the rhetorical construct known as zeugma. The dictionary entry linked above includes the example:

2) On his fishing trip, he caught three trout and a cold.

Bob Carpenter said...

Just about all linguistic interpretation involves metaphor because almost all definitions involve an analogical (i.e. example) component.

The problem with word senses is the same as for any ontology -- there's usually more than one way that makes sense to divide up the world. You can cut at different granularities. You can divide by syntactic and semantic features.

And who's to say that we all share the same senses? If they're something like mixture models we infer from evidence, people could wind up with similar predictions (or understandings) from different underlying organizations of meanings.

Also, the line between a fresh metaphor and a frozen idiom is blurry. As senses become more standardized in a community, they take on their own meaning. For instance, in 2010, nobody expects me to reason metaphorically about a computer "mouse"; I can only guess that the original metaphor involved the wire looking like a tail.

Kenahoo said...

For sense 19 ("We drove a tunnel through the hill") it might be clearer to say "safety concerns forced the mining company to drive a new tunnel through the hill". "Drove" with "a tunnel through the hill" suggests driving a car, which is not what sense 19 is about. It's about "excavating horizontally" according to WordNet.

Marine said...

Defining word senses is a thorny issue indeed....
As a non-native speaker - and okay, maybe as a MT/WSD person too :) - my first reaction when reading the example sentences was to translate them into French. It roughly gives the coarser grained OntoNotes distinctions (except for sense 2 that I would tend to split further), and also highlights literal vs. metaphorical usage: "drive cattle/cars" can be translated as "conduire", but other senses cannot.

Of course, alternate French translations or Latin or Japanese translations might give a different set of senses... So I agree with Bob that any sense inventory is arbitrary.

From a NLP perspective, one way to get around this problem is to focus on lexical substitution and crosslingual tasks: in most applications, what we really need to know is whether two words can be substituted in a given context, not whether they should be tagged with sense X, Y or Z.

Unknown said...

"Outside of a dog, a book is a man's best friend. Inside of a dog it's too dark to read."
Groucho Marx (quoted in Guy Deutscher's great book The Unfolding of Language).
Deutscher's Chapter 4, A Reef of Dead Metaphors, describes metaphors as a creative force in language. The hypothetical process described by Deutscher is a gradual transition from the concrete to the abstract through metaphors, followed by sometime loss of the middle forms. The word metaphor itself in Greek means "carry towards", which can also describe a carriage or a truck.

hal said...

@Bob: I totally agree ... this is probably why it's so hard to get agreement for WSD stuff.

I'm always amused by examples like the mouse. My favorites are when I "rewind" my DVD or my DVR, when I put stuff in my "glovebox," when I "dial" the phone, etc.

@Kenahoo: Yeah, I know that's what it's supposed to be, but I'm just really not familiar with that sense of the word.

@Marine: I agree, for those of us who speak (or try to speak) >1 language, the natural thing is to translate.

I've always wondered about metaphorical translation. I know of some negative examples. Eg., John Denero said once that their MT system was translating French "chat" into English "spade" and they discovered this was because of the idiom "call a spade a spade" being translated as "call a cat a cat" or something. But that's more idiom than metaphor.

Unfortunately, I'm not sufficiently fluent in other languages to really be able to say what the normal case is. My guess is that lots of the most common metaphors probably translate directly, but there are probably also a lot of less common ones that diverge.

ylinling001 said...

I like your article, really interesting! My point is also very good, I hope you'll like:chi flat iron are a very popular choice of hair straightener.New Balance,new Blance shoes,new Blance Outlet are some of the most comfortable and stylish shoes on the market today. The designer has a whole range of shoes for all types of athletes. five finger shoes,vibram five fingers,Five fingers shoes give women the feeling of walking barefoot while still keeping the feet protected.