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

3. 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

4. Alternatives? Semantic Grammars Information Extraction Information Retrieval

5. 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 24 th –Greeting --> {Hello|Hi|Um…} –TripRequest  Need-spec travel-verb from City to City on Date

6. Predicting User Input Semantic grammars rely upon knowledge of the task and (sometimes) constraints on what the user can do, when –Allows them to 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 from-city

7. Priming User Input Users will tend to use the vocabulary they hear from the system Explicit training vs. implicit training Training the user vs. retraining the system

8. 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 If users go outside the grammar, things may break disastrously I want to leave from my house. I want to talk to someone human.

9. Some examples Semantic grammars

10. 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 MIPS Vice President John Hime –MUC evaluationsMUC evaluations Domains: Medical texts, broadcast news (terrorist reports), voicemail,...

11. 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

12. 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?

13. 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

14. IE in SCANMail: Audio Browsing and Retrieval for Voicemail Motivated by interviews, surveys and usage logs identifying problems of heavy voicemail users: –It’s hard to quickly scan through new messages to find the ones you need to deal with (e.g. during a meeting break) –It’s hard to find the message you want in your archive –It’s hard to locate the information you want in any message (e.g. the telephone number, caller name)

15. SCANMail Architecture Caller SCANMailSubscriber

16. Corpus Details Recordings collected from 138 voicemail boxes of AT&T Labs employees 100 hours; 10,000 messages; 2500 speakers Gender balanced; 12% non-native speakers Mean message duration 36.4 secs, median 30.0 secs Hand-transcribed and annotated with caller id, gender, age, entity demarcation (names, dates, telephone numbers)

17. Transcription gender F age A caller_name NA native_speaker N speech_pathology N sample_rate 8000 label 0 804672 " [ Greeting: hi R__ ] [ CallerID: it's me ] give me a call [ um ] right away cos there's [.hn ] I guess there's some [.hn ] change [ Date: tomorrow ] with the nursery school and they [ um ] [.hn ] anyway they had this idea [ cos ] since I think J__'s the only one staying [ Date: tomorrow ] for play club so they wanted to they suggested that [.hn ] well J2__actually offered to take J__home with her and then would she would meet you back at the synagogue at [ Time: five thirty ] to pick her up [.hn ] [ uh ] so I don't know how you feel about that otherwise Miriam and one other teacher would stay and take care of her till [ Date: five thirty tomorrow ] but if you [.hn ] I wanted to know how you feel before I tell her one way or the other so call me [.hn ] right away cos I have to get back to her in about an hour so [.hn ] okay [ Closing: bye [.nhn ] [.onhk ] ]" duration "50.3 seconds"

18. Demo http://www.fancentral.org/~isenhour/scan mail/demo.html http://www.fancentral.org/~isenhour/scan mail/demo.html Audix extension: 8380 Audix extension: 8380 Audix password: (null) Audix password: (null) Audix extension: 8380 Audix password: (null) SCANMail demo SCANMail demo

19. SCANMail Demo: Number Extraction

20. SCANMail Access Devices PC Pocket PC Dataphone Voice Phone Flash E-mail

21. Finding Phone Numbers and Caller IDs (Jansche & Abney ‘02)Jansche & Abney ‘02 Goals: extract key information from msgs to present in headers from ASR transcripts Approach: –Supervised learning from transcripts (phone #’s, caller self-ids) Hand-crafted rules (good recall) propose candidates Statistical classifier (decision tree) prunes bad candidates –Features exploit structure of key elements (e.g. length of phone numbers) and surrounding context (e.g. self- ids occur at beginning of msg)

22. Location is key Predict 1=phr begin,2=in phr,3=neither Phone numbers: –Rules convert to standard digit format –Predict start with rules and prune with classifier –Position in msg and lexical cues plus length of digit string as features (.94 F on human-labeled;.95 F on ASR) Self-ids: –Predict start prediction (97% begin 1-7 words into msg) and then length of phrase (majority 2-4 words) –Avoid risk of relying on correct recognition for names –Good lexical cues to end of phrase (‘I’, ‘could’, ‘please’) (.71 F on human-labeled;.70 F on ASR)

23. 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

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

25. 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)

26. 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 t occur in D? –Inverse document frequency (idf): # docs/ # docs term t 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

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

28. Improving Queries Relevance feedback: users rate retrieved docs Query expansion: many techniques –e.g. add top N docs retrieved to query and resubmit expanded query Term clustering: cluster rows of terms to produce synonyms and add to query

29. 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 Question-answering: find a stretch of text containing the answer to a question

30. Combining IR and IE for QA Information extraction

31. 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