We introduce the Computational Linguistics special issue on Multilingual and Interlingual Semantic Representations for Natural Language Processing. We situate the special issue’s five articles in the context of our fast-changing field, explaining our motivation for this project. We offer a brief summary of the work in the issue, which includes developments on lexical and sentential semantic representations, from symbolic and neural perspectives.

We introduce a greedy transition-based parser that learns to represent parser states using recurrent neural networks. Our primary innovation that enables us to do this efficiently is a new control structure for sequential neural networks—the stack long short-term memory unit (LSTM). Like the conventional stack data structures used in transition-based parsers, elements can be pushed to or popped from the top of the stack in constant time, but, in addition, an LSTM maintains a continuous space embedding of the stack contents. Our model captures three facets of the parser's state: (i) unbounded look-ahead into the buffer of incoming words, (ii) the complete history of transition actions taken by the parser, and (iii) the complete contents of the stack of partially built tree fragments, including their internal structures. In addition, we compare two different word representations: (i) standard word vectors based on look-up tables and (ii) character-based models of words. Although standard word embedding models work well in all languages, the character-based models improve the handling of out-of-vocabulary words, particularly in morphologically rich languages. Finally, we discuss the use of dynamic oracles in training the parser. During training, dynamic oracles alternate between sampling parser states from the training data and from the model as it is being learned, making the model more robust to the kinds of errors that will be made at test time. Training our model with dynamic oracles yields a linear-time greedy parser with very competitive performance.

Recent research has shown clear improvement in translation quality by exploiting linguistic syntax for either the source or target language. However, when using syntax for both languages (“tree-to-tree” translation), there is evidence that syntactic divergence can hamper the extraction of useful rules (Ding and Palmer 2005 ). Smith and Eisner ( 2006 ) introduced quasi-synchronous grammar, a formalism that treats non-isomorphic structure softly using features rather than hard constraints. Although a natural fit for translation modeling, its flexibility has proved challenging for building real-world systems. In this article, we present a tree-to-tree machine translation system inspired by quasi-synchronous grammar. The core of our approach is a new model that combines phrases and dependency syntax, integrating the advantages of phrase-based and syntax-based translation. We report statistically significant improvements over a phrase-based baseline on five of seven test sets across four language pairs. We also present encouraging preliminary results on the use of unsupervised dependency parsing for syntax-based machine translation.

Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets (i.e., content words and phrases) in their sentential contexts and predicts frame-semantic structures. Given a target in context, the first stage disambiguates it to a semantic frame. This model uses latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time. The second stage finds the target's locally expressed semantic arguments. At inference time, a fast exact dual decomposition algorithm collectively predicts all the arguments of a frame at once in order to respect declaratively stated linguistic constraints, resulting in qualitatively better structures than naïve local predictors. Both components are feature-based and discriminatively trained on a small set of annotated frame-semantic parses. On the SemEval 2007 benchmark data set, the approach, along with a heuristic identifier of frame-evoking targets, outperforms the prior state of the art by significant margins. Additionally, we present experiments on the much larger FrameNet 1.5 data set. We have released our frame-semantic parser as open-source software.

Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures. They are used ubiquitously in computational linguistics. We present a framework, reminiscent of structural risk minimization, for empirical risk minimization of probabilistic grammars using the log-loss. We derive sample complexity bounds in this framework that apply both to the supervised setting and the unsupervised setting. By making assumptions about the underlying distribution that are appropriate for natural language scenarios, we are able to derive distribution-dependent sample complexity bounds for probabilistic grammars. We also give simple algorithms for carrying out empirical risk minimization using this framework in both the supervised and unsupervised settings. In the unsupervised case, we show that the problem of minimizing empirical risk is NP-hard. We therefore suggest an approximate algorithm, similar to expectation-maximization, to minimize the empirical risk.

This article studies the relationship between weighted context-free grammars (WCFGs), where each production is associated with a positive real-valued weight, and probabilistic context-free grammars (PCFGs), where the weights of the productions associated with a nonterminal are constrained to sum to one. Because the class of WCFGs properly includes the PCFGs, one might expect that WCFGs can describe distributions that PCFGs cannot. However, Z. Chi (1999, Computational Linguistics, 25(1):131–160) and S. P. Abney, D. A. McAllester, and P. Pereira (1999, In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 542–549, College Park, MD) proved that every WCFG distribution is equivalent to some PCFG distribution. We extend their results to conditional distributions, and show that every WCFG conditional distribution of parses given strings is also the conditional distribution defined by some PCFG, even when the WCFG's partition function diverges. This shows that any parsing or labeling accuracy improvement from conditional estimation of WCFGs or conditional random fields (CRFs) over joint estimation of PCFGs or hidden Markov models (HMMs) is due to the estimation procedure rather than the change in model class, because PCFGs and HMMs are exactly as expressive as WCFGs and chain-structured CRFs, respectively.

Parallel corpora have become an essential resource for work in multilingual natural language processing. In this article, we report on our work using the STRAND system for mining parallel text on the World Wide Web, first reviewing the original algorithm and results and then presenting a set of significant enhancements. These enhancements include the use of supervised learning based on structural features of documents to improve classification performance, a new content-based measure of translational equivalence, and adaptation of the system to take advantage of the Internet Archive for mining parallel text from the Web on a large scale. Finally, the value of these techniques is demonstrated in the construction of a significant parallel corpus for a low-density language pair.