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

Open-text semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning repre- sentation (MR – a formal representation of its sense). Unfortunately, large scale systems cannot be easily machine-learned due to a lack of directly supervised data. We propose a method that learns to assign MRs to a wide range of text (using a dictionary of more than 70,000 words mapped to more than 40,000 entities) thanks to a training scheme that combines learning from knowledge bases (e.g. WordNet) with learning from raw text. The model jointly learns representations of words, entities and MRs via a multi-task training process operating on these diverse sources of data. Hence, the system ends up providing methods for knowledge acquisition and word- sense disambiguation within the context of semantic parsing in a single elegant frame- work. Experiments on these various tasks in- dicate the promise of the approach.

Does not target a specific nonlinguistic domain.

Grounded language learning pointing to objects.

Similar to journal version.

Conversations provide rich opportunities for interactive, continuous learning. When some- thing goes wrong, a system can ask for clari- fication, rewording, or otherwise redirect the interaction to achieve its goals. In this pa- per, we present an approach for using con- versational interactions of this type to induce semantic parsers. We demonstrate learning without any explicit annotation of the mean- ings of user utterances. Instead, we model meaning with latent variables, and introduce a loss function to measure how well potential meanings match the conversation. This loss drives the overall learning approach, which in- duces a weighted CCG grammar that could be used to automatically bootstrap the semantic analysis component in a complete dialog sys- tem. Experiments on DARPA Communica- tor conversational logs demonstrate effective learning, despite requiring no explicit mean- ing annotations.

(*) Learning with logical forms provided for only part of the data (clarification questions in dialogues). Loss-sensitive perceptron (Singh-Miller and Collins 2007) DARPA communicator corpus. (Walker 2002) Access to logs of conversations where system utterances annotated, user utterances not. Annotations include speech acts (Walker and Passonneau (2001)), these are not predicted for unannotated sentences. Seems like the annotated part of the dialogue (system utterances) can be seen as training set, the rest (user utterances) as test set, is there anything new here? Uses ZC05, ZC07 (template based, not unification). Further reading: Clarke et al. (2010) and Liang et al. (2011) describe approaches for learning semantic parsers from questions paired with database answers, while Goldwasser et al. (2011) presents work on unsupervised learning. Semantic analysis tasks from context-dependent database queries (Miller et al., 1996; Zettlemoyer and Collins, 2009), grounded event streams (Chen et al., 2010; Liang et al., 2009), environment interactions (Branavan et al., 2009; 2010; Vogel and Jurafsky, 2010), and even unannotated text (Poon and Domingos, 2009; 2010). Uses BIU Number Normalizer http://www.cs.biu.ac.il/˜nlp/downloads/

The ability to understand natural-language instructions is crit- ical to building intelligent agents that interact with humans. We present a system that learns to transform natural-language navigation instructions into executable formal plans. Given no prior linguistic knowledge, the system learns by simply observing how humans follow navigation instructions. The system is evaluated in three complex virtual indoor environ- ments with numerous objects and landmarks. A previously collected realistic corpus of complex English navigation in- structions for these environments is used for training and test- ing data. By using a learned lexicon to refine inferred plans and a supervised learner to induce a semantic parser, the sys- tem is able to automatically learn to correctly interpret a rea- sonable fraction of the complex instructions in this corpus.

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.

Machine learning is traditionally formalized and researched as the study of learning concepts and decision functions from labeled examples, requir- ing a representation that encodes information about the domain of the decision function to be learned. We are interested in providing a way for a human teacher to interact with an automated learner us- ing natural instructions, thus allowing the teacher to communicate the relevant domain expertise to the learner without necessarily knowing anything about the internal representations used in the learn- ing process. In this paper we suggest to view the process of learning a decision function as a natural language lesson interpretation problem instead of learning from labeled examples. This interpretation of ma- chine learning is motivated by human learning pro- cesses, in which the learner is given a lesson de- scribing the target concept directly, and a few in- stances exemplifying it. We introduce a learning algorithm for the lesson interpretation problem that gets feedback from its performance on the final task, while learning jointly (1) how to interpret the lesson and (2) how to use this interpretation to do well on the final task. This approach alleviates the supervision burden of traditional machine learn- ing by focusing on supplying the learner with only human-level task expertise for learning. We evaluate our approach by applying it to the rules of the Freecell solitaire card game. We show that our learning approach can eventually use natural language instructions to learn the target concept and play the game legally. Furthermore, we show that the learned semantic interpreter also general- izes to previously unseen instructions.

(***) 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

We present a novel framework for learning to interpret and generate language using only per- ceptual context as supervision. We demonstrate its capabilities by developing a system that learns to sportscast simulated robot soccer games in both English and Korean without any language-specific prior knowledge. Training employs only ambiguous supervision consisting of a stream of descrip- tive textual comments and a sequence of events extracted from the simulation trace. The system simultaneously establishes correspondences between individual comments and the events that they describe while building a translation model that supports both parsing and generation. We also present a novel algorithm for learning which events are worth describing. Human evaluations of the generated commentaries indicate they are of reasonable quality and in some cases even on par with those produced by humans for our limited domain.

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 present a system that learns to fol- low navigational natural language direc- tions. Where traditional models learn from linguistic annotation or word distri- butions, our approach is grounded in the world, learning by apprenticeship from routes through a map paired with English descriptions. Lacking an explicit align- ment between the text and the reference path makes it difficult to determine what portions of the language describe which aspects of the route. We learn this corre- spondence with a reinforcement learning algorithm, using the deviation of the route we follow from the intended path as a re- ward signal. We demonstrate that our sys- tem successfully grounds the meaning of spatial terms like above and south into ge- ometric properties of paths.

Extracting knowledge from unstructured text is a long-standing goal of NLP. Al- though learning approaches to many of its subtasks have been developed (e.g., pars- ing, taxonomy induction, information ex- traction), all end-to-end solutions to date require heavy supervision and/or manual engineering, limiting their scope and scal- ability. We present OntoUSP, a system that induces and populates a probabilistic on- tology using only dependency-parsed text as input. OntoUSP builds on the USP unsupervised semantic parser by jointly forming ISA and IS-PART hierarchies of lambda-form clusters. The ISA hierar- chy allows more general knowledge to be learned, and the use of smoothing for parameter estimation. We evaluate On- toUSP by using it to extract a knowledge base from biomedical abstracts and an- swer questions. OntoUSP improves on the recall of USP by 47% and greatly outperforms previous state-of-the-art ap- proaches.

Not quite sure what they are doing here. They describe everything in geoquery but give results in biomedical? They take dependency parse as given but induce paraphrases?

A central problem in grounded language acqui- sition is learning the correspondences between a rich world state and a stream of text which refer- ences that world state. To deal with the high de- gree of ambiguity present in this setting, we present a generative model that simultaneously segments the text into utterances and maps each utterance to a meaning representation grounded in the world state. We show that our model generalizes across three domains of increasing difficulty—Robocup sportscasting, weather forecasts (a new domain), and NFL recaps.

Machine learning offers a range of tools for training systems from data, but these methods are only as good as the underly- ing representation. This paper proposes to acquire representations for machine learn- ing by reading text written to accommo- date human learning. We propose a novel form of semantic analysis called read- ing to learn, where the goal is to obtain a high-level semantic abstract of multi- ple documents in a representation that fa- cilitates learning. We obtain this abstract through a generative model that requires no labeled data, instead leveraging repe- tition across multiple documents. The se- mantic abstract is converted into a trans- formed feature space for learning, result- ing in improved generalization on a rela- tional learning task.

We present a novel commentator system that learns language from sportscasts of simulated soccer games. The system learns to parse and generate commentaries without any engineered knowledge about the English language. Training is done using only ambiguous supervision in the form of textual human commentaries and simulation states of the soccer games. The system simultaneously tries to establish correspondences between the commentaries and the simulation states as well as build a translation model. We also present a novel algorithm, Iterative Generation Strategy Learning (IGSL), for deciding which events to comment on. Human evaluations of the generated commentaries indicate they are of reasonable quality compared to human commentaries.

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.

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.

Following verbal route instructions requires knowledge of language, space, action and perception. We present MARCO, an agent that follows free-form, natural language route in- structions by representing and executing a sequence of com- pound action specifications that model which actions to take under which conditions. MARCO infers implicit actions from knowledge of both linguistic conditional phrases and from spatial action and local configurations. Thus, MARCO per- forms explicit actions, implicit actions necessary to achieve the stated conditions, and exploratory actions to learn about the world. We gathered a corpus of 786 route instructions from six peo- ple in three large-scale virtual indoor environments. Thirty- six other people followed these instructions and rated them for quality. These human participants finished at the intended destination on 69% of the trials. MARCO followed the same instructions in the same environments, with a success rate of 61%. We measured the efficacy of action inference with MARCO variants lacking action inference: executing only ex- plicit actions, MARCO succeeded on just 28% of the trials. For this task, inferring implicit actions is essential to follow poor instructions, but is also crucial for many highly-rated route instructions.

(***) 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?