In this paper, we address the relation between domain differences and domain adaptation for dependency parsing. Our quantitative analyses showed that it is the inconsistent behavior of same features cross-domain, rather than word or feature coverage, that is the major cause of performances decrease of out-domain model. We further studied those ambiguous features in depth and found that the set of ambiguous features is small and has concentric distributions. Based on the analyses, we proposed a DA method. The DA method can automatically learn which features are ambiguous cross domain according to errors made by out-domain model on in-domain training data. Our method is also extended to utilize multiple out-domain models. The results of dependency parser adaptation from WSJ to Genia and Question bank showed that our method achieved significant improvements on small in-domain datasets where DA is mostly in need. Additionally, we achieved improvement on the published best results of CoNLL07 shared task on domain adaptation, which confirms the significance of our analyses and our method.

Automatic generation of 3D scenes from descriptions has applications in communication, education, and entertainment, but requires deep understanding of the input text. I propose thesis work on language understanding using graph-based meaning representations that can be decomposed into primitive spatial relations. The techniques used for analyzing text and transforming it into a scene representation are based on context-free graph grammars. The thesis develops methods for semantic parsing with graphs, acquisition of graph grammars, and satisfaction of spatial and world-knowledge constraints during parsing.

We motivate the integration of programming by example and natural language programming by developing a system for specifying programs for simple text editing operations based on regular expressions. The programs are described with unconstrained natural language instructions, and providing one or more examples of input/output. We show that natural language allows the system to deduce the correct program much more often and much faster than is possible with the input/output example(s) alone, showing that natural language programming and programming by example can be combined in a way that overcomes the ambiguities that both methods suffer from individually, while providing a more natural interface to the user.

Semantic parsing, which aims at mapping a natural language (NL) sentence into its formal meaning representation (e.g., logical form), has received increasing attention in recent years. While synchronous context-free grammar (SCFG) augmented with lambda calculus (lambda-SCFG) provides an effective mechanism for semantic parsing, how to learn such lambda-SCFG rules still remains a challenge because of the difficulty in determining the correspondence between NL sentences and logical forms. To alleviate this structural divergence problem, we extend the GHKM algorithm, which is a state-of-the-art algorithm for learning synchronous grammars in statistical machine translation, to induce lambda-SCFG from pairs of NL sentences and logical forms. By treating logical forms as trees, we reformulate the theory behind GHKM that gives formal semantics to the alignment between NL words and logical form tokens. Experiments on the GEOQUERY dataset show that our semantic parser achieves an F-measure of 90.2%, the best result published to date.

We present a holistic data-driven technique that generates natural-language descriptions for videos. We combine the output of state-of-the-art object and activity detectors with "real-world' knowledge to select the most probable subject-verb-object triplet for describing a video. We show that this knowledge, automatically mined from web-scale text corpora, enhances the triplet selection algorithm by providing it contextual information and leads to a four-fold increase in activity identification. Unlike previous methods, our approach can annotate arbitrary videos without requiring the expensive collection and annotation of a similar training video corpus. We evaluate our technique against a baseline that does not use text-mined knowledge and show that humans prefer our descriptions 61% of the time.

In this paper, we present an approach that jointly infers the boundaries of tokens and their labels to construct dictionaries for Information Extraction. Our approach for joint-inference is based on graph propagation, and extends it in two novel ways. First, we extend the graph representation to capture ambiguities that occur during the token extraction phase. Second, we modify the labeling phase (i.e., label propagation) to utilize this new representation, allowing evidence from labeling to be used for token extraction. Our evaluation shows these extensions (and hence our approach) significantly improve the performance of the outcome dictionaries over pipeline-based approaches by preventing aggressive commitment. Our evaluation also shows that our extensions over a base graph-propagation framework improve the precision without hurting the recall.

This paper investigates incremental part of speech tagging for speech transcripts that contain multilin- gual intrasentential code-mixing, and compares the accuracy of a monolithic tagging model trained on a heterogeneous-language dataset to a model that switches between two homogeneous-language tagging models dynamically using word-by-word language identification. We find that the dynamic model, even though presented a smaller context consisting of sen- tence fragments, meets the accuracy of the monolithic code-mixing model which is aware of increased context. Our system is modular, and is designed to be expanded to many-language code-mixing.

Semantic parsing, i.e., the automatic derivation of meaning representation such as an instantiated predicate-argument structure for a sentence, plays a critical role in deep processing of natural language. Unlike all other top systems of semantic dependency parsing that have to rely on a pipeline framework to chain up a series of submodels each specialized for a specific subtask, the one presented in this article integrates everything into one model, in hopes of achieving desirable integrity and practicality for real applications while maintaining a competitive performance. This integrative approach tackles semantic parsing as a word pair classification problem using a maximum entropy classifier. We leverage adaptive pruning of argument candidates and large-scale feature selection engineering to allow the largest feature space ever in use so far in this field, it achieves a state-of-the-art performance on the evaluation data set for CoNLL-2008 shared task, on top of all but one top pipeline system, confirming its feasibility and effectiveness.

Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.

We propose a new statistical model for computational linguistics. Rather than trying to estimate directly the probability distribution of a random sentence of the language, we define a Markov chain on finite sets of sentences with many finite recurrent communicating classes and define our language model as the invariant probability measures of the chain on each recurrent communicating class. This Markov chain, that we call a communication model, recombines at each step randomly the set of sentences forming its current state, using some grammar rules. When the grammar rules are fixed and known in advance instead of being estimated on the fly, we can prove supplementary mathematical properties. In particular, we can prove in this case that all states are recurrent states, so that the chain defines a partition of its state space into finite recurrent communicating classes. We show that our approach is a decisive departure from Markov models at the sentence level and discuss its relationships with Context Free Grammars. Although the toric grammars we use are closely related to Context Free Grammars, the way we generate the language from the grammar is qualitatively different. Our communication model has two purposes. On the one hand, it is used to define indirectly the probability distribution of a random sentence of the language. On the other hand it can serve as a (crude) model of language transmission from one speaker to another speaker through the communication of a (large) set of sentences.