Robust Semantics, Information Extraction, and Information Retrieval

1. Robust Semantics, Information Extraction, and Information Retrieval CS 4705

2. Problems with Syntax-Driven Semantics • Syntactic structures often don’t fit semantic structures very well • Important semantic elements often distributed very differently in trees for sentences that mean ‘the same’ I like soup. Soup is what I like. • Parse trees contain many structural elements not clearly important to making semantic distinctions • Syntax driven semantic representations are sometimes pretty verbose V --> serves

3. Semantic Grammars • Alternative to modifying syntactic grammars to deal with semantics too • Define grammars specifically in terms of the semantic information we want to extract • Domain specific: Rules correspond directly to entities and activities in the domain I want to go from Boston to Baltimore on Thursday, September 24th • Greeting --> {Hello|Hi|Um…} • TripRequest  Need-spec travel-verb from City to City on Date

4. Predicting User Input • Rely on knowledge of task and (sometimes) constraints on what the user can do • Can handle very sophisticated phenomena I want to go to Boston on Thursday. I want to leave from there on Friday for Baltimore. TripRequest  Need-spec travel-verb from City on Date for City Dialogue postulate maps filler for ‘from-city’ to pre-specified to-city

5. Priming User Input • Users will tend to use the vocabulary they hear from the system: lexicalentrainment (Clark & Brennan ’96) • Reference to objects: the scarey M&M man • Re-use of system prompt vocabulary/syntax: Please tell me where you would like to leave/depart from. Where would you like to leave/depart from? • Explicit training vs. implicit training • Training the user vs. retraining the system

6. Drawbacks of Semantic Grammars • Lack of generality • A new one for each application • Large cost in development time • Can be very large, depending on how much coverage you want them to have • If users go outside the grammar, things may break disastrously I want to leave from my house at 10 a.m. I want to talk to a person.

7. Information Retrieval • How related to NLP? • Operates on language (speech or text) • Does it use linguistic information? • Stemming • Bag-of-words approach • Very simple analyses • Does it make use of document formatting? • Headlines, punctuation, captions • Collection: a set of documents • Term: a word or phrase • Query: a set of terms

8. But…what is a term? • Stop list • Stemming • Homonymy, polysemy, synonymy

9. Vector Space Model • Simple versions represent documents and queries as feature vectors, one binary feature for each term in collection • Is a term t in this document or in this query or not? D = (t1,t2,…,tn) Q = (t1,t2,…,tn) • Similarity metric:how many terms does a query share with each candidate document? • Weighted terms: term-by-document matrix D = (wt1,wt2,…,wtn) Q = (wt1,wt2,…,wtn)

10. How do we compare the vectors? • Normalize each term weight by the number of terms in the document: how important is each t in D? • Compute dot product between vectors to see how similar they are • Cosine of angle: 1 = identity; 0 = no common terms • How do we get the weights? • Term frequency (tf): how often does i occur inDoc j? • Inverse document frequency (idf): # docs/ # docs term i occurs in • tf . idf weighting: weight of term i for doc j is product of frequency of i in j with log of idf in collection

11. Evaluating IR Performance • Precision: #relevant docs returned/total #docs returned -- how often are you right when you say this document is relevant? • Recall: #relevant docs returned/#relevant docs in collection -- how many of the relevant documents do you find? • F-measure combines P and R • Are P and R equally important?

12. Improving Queries • Relevance feedback: users rate retrieved docs • Query expansion: many techniques • add top N docs retrieved to query and resubmit expanded query • WordNet • Term clustering: cluster rows of terms in term-by-document matrix to produce synonyms and add to query

13. IR Tasks • Ad hoc retrieval: ‘normal’ IR • Routing/categorization: assign new doc to one of predefined set of categories • Clustering: divide a collection into N clusters • Segmentation: segment text into coherent chunks • Summarization: compress a text by extracting summary items or eliminating less relevant items • Question-answering: find a span of text (within some window) containing the answer to a question

14. Information Extraction • Another ‘robust’ alternative • Idea: ‘extract’ particular types of information from arbitrary text or transcribed speech • Examples: • Named entities: people, places, organizations, times, dates • <Organization> MIPS</Organization> Vice President <Person>John Hime</Person> • MUC evaluations • Domains: Medical texts, broadcast news (terrorist reports), …

15. Appropriate where Semantic Grammars and Syntactic Parsers are not • Appropriate where information needs very specific and specifiable in advance • Question answering systems, gisting of news or mail… • Job ads, financial information, terrorist attacks • Input too complex and far-ranging to build semantic grammars • But full-blown syntactic parsers are impractical • Too much ambiguity for arbitrary text • 50 parses or none at all • Too slow for real-time applications

16. Information Extraction Techniques • Often use a set of simple templates or frames with slots to be filled in from input text • Ignore everything else • My number is 212-555-1212. • The inventor of the wiggleswort was Capt. John T. Hart. • The king died in March of 1932. • Context (neighboring words, capitalization, punctuation) provides cues to help fill in the appropriate slots • How to do better than everyone else?

17. The IE Process • Given a corpus and a target set of items to be extracted: • Clean up the corpus • Tokenize it • Do some hand labeling of target items • Extract some simple features • POS tags • Phrase Chunks … • Do some machine learning to associate features with target items or derive this associate by intuition • Use e.g. FSTs, simple or cascaded to iteratively annotate the input, eventually identifying the slot fillers

18. Domain-Specific IE from the Web (Patwardhan & Riloff ’06) • The Problem: • IE systems typically domain-specific – a new extraction procedure for every task • Supervised learning depends on hand annotation for training • Goals: • Acquire domain specific texts automatically on the Web • Identify domain-specific IE patterns automatically • Approach:

19. Start with a set of seed IE patterns learned from a hand-labeled corpus • Use these to identify relevant documents on the web • Find new seed patterns in the retrieved documents

20. MUC04 IE Task • Corpus: • 1700 news stories about terrorist events in Latin America • Answer keys about information that should be extracted • Problems: • All upper case • 50% of texts irrelevant • Stories may describe multiple events • Best results: • 50-70% precision and recall with hand-built components • 41-44% recall and 49-51% precision with automatically generated templates

21. Procedure • Apply pre-defined syntactic patterns to a training corpus of documents for which relevant/irrelevant judgments known • Count how often partial lexicalizations of each (e.g. <subj> was killed) appear in relevant vs. irrelevant documents

22. Rank patterns based on association with domain (frequency in domain documents vs. non-domain documents) • Manually review patterns and assign thematic roles to those deemed useful • From 40K+ patterns  291 • Now find similar web documents

23. Domain Corpus Creation • Create IR queries by crossing names of 5 terrorist organizations (e.g. Al Qaeda, IRA) with 16 terrorist activities (e.g assinated, bombed, hijacked, wounded)  80 queries • Restricted to CNN, English documents • Eliminated TV transcripts • Yield from 2 runs: 6,182 documents • Cleaned corpus: 5,618 documents

24. Learning Domain-Specific Patterns • Hypothesis: new extraction patterns co-occurring with seed patterns from training corpus will also be associated with terrorism • Generate all extraction patterns in CNN corpus (147,712) • Compute correlation of each with seed patterns based on frequency of co-occurrence in same sentence – keep those occurring more often that chance with some seed • Rank new patterns by their seed correlations

25. Highly Ranked Patterns • Filter: Measure semantic affinity: how often does this pattern extract an entity of a particular category (e.g. victim, target)? • Compute semantic affinity for each extraction pattern wrt 6 categories: target, victim plus distractors: perpetrator, organization, weapon, other • E.g. Frequency of extracting target/frequency of extracting any of 6 categories weighted by log probability of target

26. Remove patterns not strongly associated with desired classes: • Evaluate on MUC-4 • Baseline: • Recall 64%/Precision 43% on targets • Recall 50%/Precision 52% on victims

27. Results for Web-Learned Patterns • Use 396 terrorism extraction patterns learned from MUC training set as seeds • Produce ranked list of new patterns from web using semantic affinity of 3.0 threshold • Chose top N (50-300) patterns to add to seed set • Performance:

28. Combining IR and IE for QA • Information extraction: AQUA

29. Summary • Many approaches to ‘robust’ semantic analysis • Semantic grammars targeting particular domains Utterance --> Yes/No Reply Yes/No Reply --> Yes-Reply | No-Reply Yes-Reply --> {yes,yeah, right, ok,”you bet”,…} • Information extraction techniques targeting specific tasks • Extracting information about terrorist events from news • Information retrieval techniques --> more like NLP