A probabilistic Chomsky–Schützenberger hierarchy of grammars is introduced and studied, with the aim of understanding the expressive power of generative models. We offer characterizations of the distributions definable at each level of the hierarchy, including probabilistic regular, context-free, (linear) indexed, context-sensitive, and unrestricted grammars, each corresponding to familiar probabilistic machine classes. Special attention is given to distributions on (unary notations for) positive integers. Unlike in the classical case where the "semi-linear" languages all collapse into the regular languages, using analytic tools (...) adapted from the classical setting we show there is no collapse in the probabilistic hierarchy: more distributions become definable at each level. We also address related issues such as closure under probabilistic conditioning. (shrink)

Appellate Court Modifications Extraction consists of, given an Appellate Court decision, identifying the proposed modifications by the upper Court of the lower Court judge’s decision. In this work, we propose a system to extract Appellate Court Modifications for Portuguese. Information extraction for legal texts has been previously addressed using different techniques and for several languages. Our proposal differs from previous work in two ways: our corpus is composed of Brazilian Appellate Court decisions, in which we look for a set of (...) modifications provided by the Court; and to automatically extract the modifications, we use a traditional Machine Learning approach and a Deep Learning approach, both as alternative solutions and as a combined solution. We tackle the Appellate Court Modifications Extraction task, experimenting with a wide variety of methods. In order to train and evaluate the system, we have built the KauaneJunior corpus, using public data disclosed by the Appellate State Court of Rio de Janeiro jurisprudence database. Our best method, which is a Bidirectional Long Short-Term Memory network combined with Conditional Random Fields, obtained an \ score of 94.79%. (shrink)

This paper examines the Stanford typed dependencies representation, which was designed to provide a straightforward description of grammatical relations for any user who could benefit from automatic text understanding. For such purposes, we argue that dependency schemes must follow a simple design and provide semantically contentful information, as well as offer an automatic procedure to extract the relations. We consider the underlying design principles of the Stanford scheme from this perspective, and compare it to the GR and PARC representations. Finally, (...) we address the question of the suitability of the Stanford scheme for parser evaluation. (shrink)

Marie-Catherine de Marneffe, Anna N. Rafferty and Christopher D. Manning Linguistics Department Computer Science Department Stanford University Stanford University Stanford, CA 94305 Stanford, CA 94305 {rafferty,manning}@stanford.edu [email protected]..

We examine the expressive power of probabilistic context free grammars (PCFGs), with a special focus on the use of probabilities as a mechanism for reducing ambiguity by filtering out unwanted parses. Probabilities in PCFGs induce an ordering relation among the set of trees that yield a given input sentence. PCFG parsers return the trees bearing the maximum probability for a given sentence, discarding all other possible trees. This mechanism is naturally viewed as a way of defining a new class of (...) tree languages. We formalize the tree language thus defined, study its expressive power, and show that the latter is beyond context freeness. While the increased expressive power offered by PCFGs helps to reduce ambiguity, we show that, in general, it cannot be decided whether a PCFG removes all ambiguities. (shrink)

This paper proposes several recurrent neural network-based models for recognizing requisite and effectuation parts in Legal Texts. Firstly, we propose a modification of BiLSTM-CRF model that allows the use of external features to improve the performance of deep learning models in case large annotated corpora are not available. However, this model can only recognize RE parts which are not overlapped. Secondly, we propose two approaches for recognizing overlapping RE parts including the cascading approach which uses the sequence of BiLSTM-CRF models (...) and the unified model approach with the multilayer BiLSTM-CRF model and the multilayer BiLSTM-MLP-CRF model. Experimental results on two Japan law RRE datasets demonstrated advantages of our proposed models. For the Japanese National Pension Law dataset, our approaches obtained an \ score of 93.27% and exhibited a significant improvement compared to previous approaches. For the Japan Civil Code RRE dataset which is written in English, our approaches produced an \ score of 78.24% in recognizing RE parts that exhibited a significant improvement over strong baselines. In addition, using external features and in-domain pre-trained word embeddings also improved the performance of RRE systems. (shrink)

This paper presents the first use of a computational model of natural logic—a system of logical inference which operates over natural language—for textual inference. Most current approaches to the PAS- CAL RTE textual inference task achieve robustness by sacrificing semantic precision; while broadly effective, they are easily confounded by ubiquitous inferences involving monotonicity. At the other extreme, systems which rely on first-order logic and theorem proving are precise, but excessively brittle. This work aims at a middle way. Our system finds (...) a low-cost edit sequence which transforms the premise into the hypothesis; learns to classify entailment relations across atomic edits; and composes atomic entailments into a top-level entailment judgment. We provide the first reported results for any system on the FraCaS test suite. We also evaluate on RTE3 data, and show that hybridizing an existing RTE system with our natural logic system yields significant performance gains. (shrink)

This paper describes a system for extracting typed dependency parses of English sentences from phrase structure parses. In order to capture inherent relations occurring in corpus texts that can be critical in real-world applications, many NP relations are included in the set of grammatical relations used. We provide a comparison of our system with Minipar and the Link parser. The typed dependency extraction facility described here is integrated in the Stanford Parser, available for download.

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data. Our efficiency is primarily due to the use of stochastic optimization techniques, as well as parallelization and chart prefiltering. On WSJ15, (...) we attain a state-of-the-art F-score of 90.9%, a 14% relative reduction in error over previous models, while being two orders of magnitude faster. On sentences of length 40, our system achieves an F-score of 89.0%, a 36% relative reduction in error over a generative baseline. (shrink)

Ben Taskar Dan Klein Michael Collins Computer Science Dept. Computer Science Dept. CS and AI Lab Stanford University Stanford University.

tic structure. Determining the semantic roles of a verb’s dependents is an important step in natural..

number of hidden categories is not fixed, but when the number of hidden states is unknown (Beal et al., 2002; Teh et al., 2006). can grow with the amount of training data.

I examine what would be necessary to move part-of-speech tagging performance from its current level of about 97.3% token accuracy (56% sentence accuracy) to close to 100% accuracy. I suggest that it must still be possible to greatly increase tagging performance and examine some useful improvements that have recently been made to the Stanford Part-of-Speech Tagger. However, an error analysis of some of the remaining errors suggests that there is limited further mileage to be had either from better machine learning (...) or better features in a discriminative sequence classifier. The prospects for further gains from semisupervised learning also seem quite limited. Rather, I suggest and begin to demonstrate that the largest opportunity for further progress comes from improving the taxonomic basis of the linguistic resources from which taggers are trained. That is, from improved descriptive linguistics. However, I conclude by suggesting that there are also limits to this process. The status of some words may not be able to be adequately captured by assigning them to one of a small number of categories. While conventions can be used in such cases to improve tagging consistency, they lack a strong linguistic basis. (shrink)

We propose an approach to natural language inference based on a model of natural logic, which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation. We greatly extend past work in natural logic, which has focused solely on semantic containment and monotonicity, to incorporate both semantic exclusion and implicativity. Our system decomposes an inference problem into a sequence of atomic edits linking premise to hypothesis; predicts a lexical entailment relation for each edit using a statistical classifier; (...) propagates these relations upward through a syntax tree according to semantic properties of intermediate nodes; and composes the resulting entailment relations across the edit sequence. We evaluate our system on the FraCaS test suite, and achieve a 27% reduction in error from previous work. We also show that hybridizing an existing RTE system with our natural logic system yields significant gains on the RTE3 test suite. (shrink)

separated from evaluating entailment. Current approaches to semantic inference in question answer-.

Name der Zeitschrift: Cognitive Linguistics Jahrgang: 27 Heft: 2 Seiten: 235-268.

We examine the expressive power of probabilistic context free grammars (PCFGs), with a special focus on the use of probabilities as a mechanism for reducing ambiguity by filtering out unwanted parses. Probabilities in PCFGs induce an ordering relation among the set of trees that yield a given input sentence. PCFG parsers return the trees bearing the maximum probability for a given sentence, discarding all other possible trees. This mechanism is naturally viewed as a way of defining a new class of (...) tree languages. We formalize the tree language thus defined, study its expressive power, and show that the latter is beyond context freeness. While the increased expressive power offered by PCFGs helps to reduce ambiguity, we show that, in general, it cannot be decided whether a PCFG removes all ambiguities. (shrink)