Use of Modality and Negation in Semantically-Informed Syntactic MT
U.S. Dept. of Defense（美国国防部）；University of Maryland（马里兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Carnegie Mellon University（卡内基梅隆大学）；BBN Technologies（BBN科技公司）
Kathryn Baker, Michael Bloodgood, Bonnie J. Dorr, Chris Callison-Burch, Nathaniel W. Filardo, Christine Piatko, Lori Levin, Scott Miller
备注：
28 pages, 13 figures, 2 tables; appeared in Computational Linguistics, 38(2):411-438, 2012
This paper describes the resource- and system-building efforts of an eight-week Johns Hopkins University Human Language Technology Center of Excellence Summer Camp for Applied Language Exploration (SCALE-2009) on Semantically-Informed Machine Translation (SIMT). We describe a new modality/negation (MN) annotation scheme, the creation of a (publicly available) MN lexicon, and two automated MN taggers that we built using the annotation scheme and lexicon. Our annotation scheme isolates three components of modality and negation: a trigger (a word that conveys modality or negation), a target (an action associated with modality or negation) and a holder (an experiencer of modality). We describe how our MN lexicon was semi-automatically produced and we demonstrate that a structure-based MN tagger results in precision around 86% (depending on genre) for tagging of a standard LDC data set.
We apply our MN annotation scheme to statistical machine translation using a syntactic framework that supports the inclusion of semantic annotations. Syntactic tags enriched with semantic annotations are assigned to parse trees in the target-language training texts through a process of tree grafting. While the focus of our work is modality and negation, the tree grafting procedure is general and supports other types of semantic information. We exploit this capability by including named entities, produced by a pre-existing tagger, in addition to the MN elements produced by the taggers described in this paper. The resulting system significantly outperformed a linguistically naive baseline model (Hiero), and reached the highest scores yet reported on the NIST 2009 Urdu-English test set. This finding supports the hypothesis that both syntactic and semantic information can improve translation quality.
U.S. Dept. of Defense（美国国防部）；JHU HLTCOE（约翰斯·霍普金斯大学人类语言技术卓越中心）；University of Maryland（马里兰大学）；CMU（卡内基梅隆大学）；BBN（BBN公司）；JHU/APL（约翰斯·霍普金斯大学应用物理实验室）
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts improved translation quality. The resulting system significantly outperformed a linguistically naive baseline model (Hiero), and reached the highest scores yet reported on the NIST 2009 Urdu-English translation task. This finding supports the hypothesis (posed by many researchers in the MT community, e.g., in DARPA GALE) that both syntactic and semantic information…
Robotic commands in natural language usually contain various spatial descriptions that are semantically similar but syntactically different. Mapping such syntactic variants into semantic concepts that can be understood by robots is challenging due to the high flexibility of natural language expressions. To tackle this problem, we collect robotic commands for navigation and manipulation tasks using crowdsourcing. We further define a robot language and use a generative machine translation model to translate robotic commands from natural language to robot language. The main purpose of this paper …
We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of semantically equivalent sentences, while maintaining sufficient distance between those of dissimilar sentences. The models do not rely on word alignments or any syntactic information and are successfully applied to a number of diverse languages. We extend our approach to learn semantic representations at the document level, too. We evaluate these models on …
The George Washington University（乔治华盛顿大学）；University of Pennsylvania（宾夕法尼亚大学）
We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available. We leverage a multitask learning framework coupled with an annotation projection method. We transfer supervised semantic dependency parse annotations from a rich-resource language to a low-resource language through parallel data, and train a semantic parser on projected data. We make use of supervised syntactic parsing as an auxiliary task in a multitask learning framework, and show that with different multitask learning settings, we consistent…
National Institutes of Health（美国国立卫生研究院）；The Ohio State University（俄亥俄州立大学）
Assessing how individuals perform different activities is key information for modeling health states of individuals and populations. Descriptions of activity performance in clinical free text are complex, including syntactic negation and similarities to textual entailment tasks. We explore a variety of methods for the novel task of classifying four types of assertions about activity performance: Able, Unable, Unclear, and None (no information). We find that ensembling an SVM trained with lexical features and a CNN achieves 77.9% macro F1 score on our task, and yields nearly 80% recall on the r…
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）；Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所）；International Max Planck Research School for Language Sciences（马克斯·普朗克语言科学国际研究学校）；Donders Institute for Brain, Cognition, and Behaviour, Radboud University（拉德布德大学德登斯脑认知与行为研究所）；Department of Psychology, University of Alberta（阿尔伯塔大学心理学系）
The representations generated by many models of language (word embeddings, recurrent neural networks and transformers) correlate to brain activity recorded while people read. However, these decoding results are usually based on the brain's reaction to syntactically and semantically sound language stimuli. In this study, we asked: how does an LSTM (long short term memory) language model, trained (by and large) on semantically and syntactically intact language, represent a language sample with degraded semantic or syntactic information? Does the LSTM representation still resemble the brain's rea…
Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between non-headwords. We show that non-headword dependencies contribute to significantly improved word error rate, and that a data-oriented parsing model trained on semantically and syntactically annotated data can exploit these dependencies. This paper also contains the first DOP model trained by means of a maximum likelihood reestimation procedure, which solves some of the …
Universitat Rovira i Virgili（罗维拉-威尔吉利大学）；University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；New York University（纽约大学）
Machine intelligence is increasingly being linked to claims about sentience, language processing, and an ability to comprehend and transform natural language into a range of stimuli. We systematically analyze the ability of DALL-E 2 to capture 8 grammatical phenomena pertaining to compositionality that are widely discussed in linguistics and pervasive in human language: binding principles and coreference, passives, word order, coordination, comparatives, negation, ellipsis, and structural ambiguity. Whereas young children routinely master these phenomena, learning systematic mappings between s…
Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks. In this work, we tackle the task of unsupervised disentanglement between semantics and structure in neural language representations: we aim to learn a transformation of the contextualized vectors, that discards the lexical semantics, but keeps the structural information. To this end, we automatically generate groups of sentences which are structurally similar but semantically different, and use metric-learning approach to learn a transformation that emphasizes the str…
We computed linguistic information at the lexical, syntactic, and semantic levels for Recognizing Inference in Text (RITE) tasks for both traditional and simplified Chinese in NTCIR-9 and NTCIR-10. Techniques for syntactic parsing, named-entity recognition, and near synonym recognition were employed, and features like counts of common words, statement lengths, negation words, and antonyms were considered to judge the entailment relationships of two statements, while we explored both heuristics-based functions and machine-learning approaches. The reported systems showed robustness by simultaneo…
In Data-Oriented Parsing (DOP), an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new input sentence is constructed by combining sub-analyses from the corpus in the most probable way. This approach has been succesfully used for syntactic analysis, using corpora with syntactic annotations such as the Penn Treebank. If a corpus with semantically annotated sentences is used, the same approach can also generate the most probable semantic interpretation of an input sentence. The present paper explains this semantic interpretation method, and summarizes th…
Analysis of vision-and-language models has revealed their brittleness under linguistic phenomena such as paraphrasing, negation, textual entailment, and word substitutions with synonyms or antonyms. While data augmentation techniques have been designed to mitigate against these failure modes, methods that can integrate this knowledge into the training pipeline remain under-explored. In this paper, we present \textbf{SDRO}, a model-agnostic method that utilizes a set linguistic transformations in a distributed robust optimization setting, along with an ensembling technique to leverage these tra…
Question Generation (QG) is fundamentally a simple syntactic transformation; however, many aspects of semantics influence what questions are good to form. We implement this observation by developing SynQG, a set of transparent syntactic rules leveraging universal dependencies, shallow semantic parsing, lexical resources, and custom rules which transform declarative sentences into question-answer pairs. We utilize PropBank argument descriptions and VerbNet state predicates to incorporate shallow semantic content, which helps generate questions of a descriptive nature and produce inferential and…
Underutilization of Syntactic Processing by Chinese Learners of English in Comprehending English Sentences, Evidenced from Adapted Garden-Path Ambiguity Experiment
Center for Language and Cognition, University of Groningen（格罗宁根大学语言与认知中心）
This paper gives a general description of the ideas behind the Parallel Meaning Bank, a framework with the aim to provide an easy way to annotate compositional semantics for texts written in languages other than English. The annotation procedure is semi-automatic, and comprises seven layers of linguistic information: segmentation, symbolisation, semantic tagging, word sense disambiguation, syntactic structure, thematic role labelling, and co-reference. New languages can be added to the meaning bank as long as the documents are based on translations from English, but also introduce new interest…
The syntactic topic model (STM) is a Bayesian nonparametric model of language that discovers latent distributions of words (topics) that are both semantically and syntactically coherent. The STM models dependency parsed corpora where sentences are grouped into documents. It assumes that each word is drawn from a latent topic chosen by combining document-level features and the local syntactic context. Each document has a distribution over latent topics, as in topic models, which provides the semantic consistency. Each element in the dependency parse tree also has a distribution over the topics …
Qatar Computing Research Institute, Hamad Bin Khalifa University（哈马德·本·哈利法大学卡塔尔计算研究所）
In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing techniques based on diagnostic classifiers, we assess the accuracy of representing constituents of different categories within the neuron activations of a LM such as RoBERTa. In order to make sure that our probe focuses on syntactic knowledge and not on implicit semantic generalizations, we also experiment on a PTB version that is obtained by randomly repla…
The University of Tokyo（东京大学）；RIKEN（理化学研究所）；Keio University（庆应义塾大学）；Tohoku University（东北大学）
Recently, deep neural networks (DNNs) have achieved great success in semantically challenging NLP tasks, yet it remains unclear whether DNN models can capture compositional meanings, those aspects of meaning that have been long studied in formal semantics. To investigate this issue, we propose a Systematic Generalization testbed based on Natural language Semantics (SyGNS), whose challenge is to map natural language sentences to multiple forms of scoped meaning representations, designed to account for various semantic phenomena. Using SyGNS, we test whether neural networks can systematically pa…
Nominalization is a highly productive phenomena in most languages. The process of nominalization ejects a verb from its syntactic role into a nominal position. The original verb is often replaced by a semantically emptied support verb (e.g., "make a proposal"). The choice of a support verb for a given nominalization is unpredictable, causing a problem for language learners as well as for natural language processing systems. We present here a method of discovering support verbs from an untagged corpus via low-level syntactic processing and comparison of arguments attached to verbal forms and po…
The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs, is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that large-size pre-trained language models (PLMs) do not satisfy this property. In this paper, we perform experiments using probing tasks to assess PLM's LNP understanding. Unlike previous studies that only examined negation expressions, we expand the boundary of the investigation to lexical semantics. Through experiments, we observe that PLMs violate the LNP frequently…
Johns Hopkins University（约翰斯·霍普金斯大学）；New York University（纽约大学）
We present COD3S, a novel method for generating semantically diverse sentences using neural sequence-to-sequence (seq2seq) models. Conditioned on an input, seq2seq models typically produce semantically and syntactically homogeneous sets of sentences and thus perform poorly on one-to-many sequence generation tasks. Our two-stage approach improves output diversity by conditioning generation on locality-sensitive hash (LSH)-based semantic sentence codes whose Hamming distances highly correlate with human judgments of semantic textual similarity. Though it is generally applicable, we apply COD3S t…
In this article, we propose an automatic process to build multi-lingual lexico-semantic resources. The goal of these resources is to browse semantically textual information contained in texts of different languages. This method uses a mathematical model called Atlas sémantiques in order to represent the different senses of each word. It uses the linguistic relations between words to create graphs that are projected into a semantic space. These projections constitute semantic maps that denote the sense trends of each given word. This model is fed with syntactic relations between words extracted…
Galatasaray University（加拉塔萨雷大学）；TÜBİTAK（土耳其科学技术研究委员会）；University of Corsica（科西嘉大学）
Many recent works aim at developing methods and tools for the processing of semantic Web services. In order to be properly tested, these tools must be applied to an appropriate benchmark, taking the form of a collection of semantic WS descriptions. However, all of the existing publicly available collections are limited by their size or their realism (use of randomly generated or resampled descriptions). Larger and realistic syntactic (WSDL) collections exist, but their semantic annotation requires a certain level of automation, due to the number of operations to be processed. In this article, …
