Articles

This paper describes DUALIST, an active learning annotation paradigm which solicits and learns from labels on both features (e.g., words) and instances (e.g., documents). We present a novel semi-supervised training al- gorithm developed for this setting, which is (1) fast enough to support real-time interac- tive speeds, and (2) at …...

Modelling compositional meaning for sen- tences using empirical distributional methods has been a challenge for computational lin- guists. We implement the abstract categorical model of Coecke et al. (2010) using data from the BNC and evaluate it. The implementation is based on unsupervised learning of matrices for relational words and …...

Mining of transliterations from comparable or parallel text can enhance natural language processing applications such as machine translation and cross language information retrieval. This paper presents an enhanced transliteration mining technique that uses a generative graph reinforcement model to infer mappings between source and target character sequences. An initial set …...

Most traditional summarization methods treat their outputs as static and plain texts, which fail to capture user interests during summa- rization because the generated summaries are the same for different users. However, users have individual preferences on a particular source document collection and obviously a universal summary for all users …...

Based on analysis of on-line review corpus we observe that most sentences have compli- cated opinion structures and they cannot be well represented by existing methods, such as frame-based and feature-based ones. In this work, we propose a novel graph-based rep- resentation for sentence level sentiment. An integer linear programming-based …...

In this paper we present a method for unsuper- vised semantic role induction which we for- malize as a graph partitioning problem. Ar- gument instances of a verb are represented as vertices in a graph whose edge weights quan- tify their role-semantic similarity. Graph par- titioning is realized with an …...

This paper compares several translation rep- resentations for a synchronous context-free grammar parse including CFGs/hypergraphs, finite-state automata (FSA), and pushdown automata (PDA). The representation choice is shown to determine the form and complex- ity of target LM intersection and shortest-path algorithms that follow. Intersection, shortest path, FSA expansion and RTN …...

Information published in online stock invest- ment message boards, and more recently in stock microblogs, is considered highly valu- able by many investors. Previous work fo- cused on aggregation of sentiment from all users. However, in this work we show that it is beneficial to distinguish expert users from non-experts. …...

Accurate prediction of demographic attributes from social media and other informal online content is valuable for marketing, personalization, and legal in- vestigation. This paper describes the construction of a large, multilingual dataset labeled with gender, and investigates statistical models for determining the gender of uncharacterized Twitter users. We explore several …...

We propose a novel way of incorporating de- pendency parse and word co-occurrence in- formation into a state-of-the-art web-scale n- gram model for spelling correction. The syn- tactic and distributional information provides extra evidence in addition to that provided by a web-scale n-gram corpus and especially helps with data sparsity …...

We show that categories induced by unsuper- vised word clustering can surpass the perfor- mance of gold part-of-speech tags in depen- dency grammar induction. Unlike classic clus- tering algorithms, our method allows a word to have different tags in different contexts. In an ablative analysis, we first demonstrate that this …...

We present new training methods that aim to mitigate local optima and slow convergence in unsupervised training by using additional im- perfect objectives. In its simplest form, lateen EM alternates between the two objectives of ordinary “soft” and “hard” expectation max- imization (EM) algorithms. Switching objec- tives when stuck can …...

Dependency parsers are critical components within many NLP systems. However, cur- rently available dependency parsers each ex- hibit at least one of several weaknesses, in- cluding high running time, limited accuracy, vague dependency labels, and lack of non- projectivity support. Furthermore, no com- monly used parser provides additional shal- low …...

We describe a generative model for non- projective dependency parsing based on a sim- plified version of a transition system that has recently appeared in the literature. We then develop a dynamic programming parsing al- gorithm for our model, and derive an inside- outside algorithm that can be used for …...

This paper introduces Chart Inference (CI), an algorithm for deriving a CCG category for an unknown word from a partial parse chart. It is shown to be faster and more pre- cise than a baseline brute-force method, and to achieve wider coverage than a rule-based system. In addition, we show …...

This paper develops a framework for syntac- tic dependency parse correction. Dependen- cies in an input parse tree are revised by se- lecting, for a given dependent, the best gov- ernor from within a small set of candidates. We use a discriminative linear ranking model to select the best governor …...

The notion of infix probability has been intro- duced in the literature as a generalization of the notion of prefix (or initial substring) prob- ability, motivated by applications in speech recognition and word error correction. For the case where a probabilistic context-free gram- mar is used as language model, methods …...

The computation of logical form has been pro- posed as an intermediate step in the translation of sentences to logic. Logical form encodes the resolution of scope ambiguities. In this paper, we describe experiments on a modest- sized corpus of regulation annotated with a novel variant of logical form, called …...

We propose a relaxed correspondence as- sumption for cross-lingual projection of con- stituent syntax, which allows a supposed constituent of the target sentence to corre- spond to an unrestricted treelet in the source parse. Such a relaxed assumption fundamen- tally tolerates the syntactic non-isomorphism between languages, and enables us to …...

Part-of-speech (POS) is an indispensable fea- ture in dependency parsing. Current research usually models POS tagging and dependency parsing independently. This may suffer from error propagation problem. Our experiments show that parsing accuracy drops by about 6% when using automatic POS tags instead of gold ones. To solve this issue, …...