Learns from q/a pairs in the geo and jobs data.

Current approaches for semantic parsing take a supervised approach requiring a consider- able amount of training data which is expen- sive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data, and in- troduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. Evaluated over Geoquery, a standard dataset for this task, our system achieved 66% accuracy, com- pared to 80% of its fully supervised counter- part, demonstrating the promise of unsuper- vised approaches for this task.

(***) Build on unification based Kwiatkowski 2010. Key observation is groups of words show same syntactic/semantic tag variation. So learn the variation for the whole group, more robust to data sparsity. i.e. They have discovered that word classes exist :) This helps generalize the language-independent unification approach to unedited sentences like in atis. Mentions Clarke10, Liang11, Goldwasser11 as going from sentences to answers without LF. Mentions Branavan10, Vogel10, Liang09, Poon09, 10 as learning from interactions. Results: (ubl: Kwiatkowsky10, fubl: Kwiatkowski11) atis-exact-f1: zc07:.852 ubl:.717 fubl:.828 geo880-f1: zc05:.870 zc07:.888 ubl:.882 fubl:.886 geo250-en: wasp:.829 ubl:.826 fubl:.837 geo250-sp: wasp:.858 ubl:.824 fubl:.857 geo250-jp: wasp:.858 ubl:.831 fubl:.835 geo250-tr: wasp:.781 ubl:.746 fubl:.731

Current approaches to semantic parsing, the task of converting text to a formal meaning representation, rely on annotated training data mapping sentences to logi- cal forms. Providing this supervision is a major bottleneck in scaling semantic parsers. This paper presents a new learn- ing paradigm aimed at alleviating the su- pervision burden. We develop two novel learning algorithms capable of predicting complex structures which only rely on a binary feedback signal based on the con- text of an external world. In addition we reformulate the semantic parsing problem to reduce the dependency of the model on syntactic patterns, thus allowing our parser to scale better using less supervision. Our results surprisingly show that without us- ing any annotated meaning representations learning with a weak feedback signal is ca- pable of producing a parser that is compet- itive with fully supervised parsers.

(****) Sentence to logical form mapping using CCG and unification (UBL) instead of GenLex. Geo dataset, four languages, two meaning representations (funql, lambda). Start with single lex item for each sentence mapping it to LF. Introduce vertical bar | to ccg which can match / or \. (ZC07 similar?) Understand the SGD gradient possibly reading CC07. Starting with single lex item and trying splits look much less ad-hoc than ZC05,07 with Genlex and initial lexicon. Only the proper noun NPs (e.g. Texas) are in the initial lexicon. 4.1 splitting constraints interesting, can learn them from data? The split-merge process seem a bit ad-hoc, a more principled Bayesian approach may be possible. Good related work discussion in Sec 6. UBL geo880: p=.941 r=.850 f=.893 UBL-s (2pass): p=.885 r=.879 f=.882

We consider the problem of learning to parse sentences to lambda-calculus representations of their underlying semantics and present an algorithm that learns a weighted combinatory categorial grammar (CCG). A key idea is to introduce non-standard CCG combinators that relax certain parts of the grammar—for example allowing flexible word order, or insertion of lexical items— with learned costs. We also present a new, online algorithm for inducing a weighted CCG. Results for the approach on ATIS data show 86 % F-measure in recovering fully correct semantic analyses and 95.9% F-measure by a partial-match criterion, a more than 5 % improvement over the 90.3% partial-match figure reported by He and Young (2006).

(*) Solving the same problem as ZC05 paper on atis and geo. Geo, jobs, restaurant are artificially generated, atis is natural! New CCG combinators and new online algorithm more flexible with realistic language. atis exact 1-pass p=.9061 r=.8192 f=.8605 atis exact 2-pass p=.8575 r=.8460 f=.8516 atis partial 1-pass p=.9676 r=.8689 f=.9156 atis partial 2-pass p=.9511 r=.9671 f=.9590 (He and Young 2006 atis partial f=90.3%) geo880 1-pass p=.9549 r=.8320 f=.8893 geo880 2-pass p=.9163 r=.8607 f=.8876 (ZC05 p=.9625 r=.7929 f=.8695) Still uses GENLEX with two additional rules. Still uses initial lexicon with nouns and wh-words! CCG additions include: 1. function application with reverse word order. 2. function composition with reverse word order. (do we even need the syntactic cats with slashes?) 3. additional type raising and crossed-comp rules that need more careful reading. Two important differences from learning algorithm of ZC05: 1. online updates instead of batch. 2. perceptron updates instead of SGD on NLL. Learning algorithm: 1. skip example if parsed correctly with current lex. 2. introduce all genlex and find maxscore parse with correct semantics. 3. add the new entries in maxparse to lex and try parsing again. 4. do a perceptron update.

This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of nat- ural language sentences annotated with multiple potential meaning representations, only one of which is correct. Such ambiguous supervision models the type of supervision that can be more naturally available to language-learning systems. Given such weak supervision, our approach produces a se- mantic parser that maps sentences into meaning represen- tations. An existing semantic parsing learning system that can only learn from unambiguous supervision is augmented to handle ambiguous supervision. Experimental results show that the resulting system is able to cope up with ambiguities and learn accurate semantic parsers.

(***) Zettlemoyer and Collins 2005: map sentences to typed lambda expressions: which rivers run through states that border the state with the capital austin (lambda $0:e (and:<t*,t> (river:<r,t> $0) (exists:<<e,t>,t> (lambda $1:e (and:<t*,t> (state:<s,t> $1) (next_to:<lo,<lo,t>> $1 (the:<<e,t>,e> (lambda $2:e (and:<t*,t> (state:<s,t> $2) (capital2:<s,<c,t>> $2 austin_tx:c))))) (loc:<lo,<lo,t>> $0 $1)))))) In addition to the training set of pairs like above they have two additional sources of information given by hand: a. GENLEX rules: to generate candidates for the lexicon, they produce a cross product of (all substrings of the sentence) x (all categories that can be produced from the lambda expression). The second part is done using 10 heuristic rules that convert parts of the lambda expression to possible categories e.g. N:(lambda (x) (major x)). b. Initial lexicon: this includes two types of manually added entries: domain specific, database derived entities such as (Utah => NP:utah) and domain independent entries such as “what” => (S/(S\NP))/N:(lambda f (lambda g (lamba x (and (f x) (g x)))). Both these look like cheating. How sensitive are the results to these manual inputs? What kinds of words are actually learnt at the end? Is it possible to learn entries like “what” at all? Why do we need syntactic categories, can’t we just have lambda expressions? Should look at how future work handled these. Geo880 p=.9625 r=.7929 f=.8695 (TM01 p=.8992 r=.7940) Jobs640 p=.9736 r=.7929 f=.8740 (TM01 p=.9325 r=.7984)

First introduced geoquery?