Sign language models are predominantly trained with gloss-sequence or text supervision, thereby under-modeling non-lexical and productive constructions. One comparatively tractable instance is spatial indexing: pointing gestures that assign discourse entities to spatial loci for subsequent co-reference, which lexicon-centric objectives largely fail to capture. We present a targeted evaluation of indexing in Sign Language Recognition, showing that despite comprising 10-15% of signing content, indexing is poorly recovered. We introduce a framework for training and evaluating indexing experts, establishing a baseline for index-aware sign language modeling. Our approach decomposes spatial reference resolution into index detection and discourse entity linking. The resulting mention representations enable automatic annotation and non-lexical structure modeling, and serve as an auxiliary indexing expert that augments a frozen SLR model at inference time.
This paper defines multiset-valued linear index grammar and unordered vector grammar with dominance links. The former models certain uses of multiset-valued feature structures in unification-based formalisms, while the latter is motivated by word order variation and by ``quasi-trees'', a generalization of trees. The two formalisms are weakly equivalent, and an important subset is at most context-sensitive and polynomially parsable.
Indexed languages are interesting in computational linguistics because they are the least class of languages in the Chomsky hierarchy that has not been shown not to be adequate to describe the string set of natural language sentences. We here define a class of unification grammars that exactly describe the class of indexed languages.
This paper presents a grammar formalism designed for use in data-oriented approaches to language processing. The formalism is best described as a right-linear indexed grammar extended in linguistically interesting ways. The paper goes on to investigate how a corpus pre-parsed with this formalism may be processed to provide a probabilistic language model for use in the parsing of fresh texts.
Octanove Labs；University of Washington（华盛顿大学）；University of Tokyo（东京大学）；Allen Institute for AI（艾伦人工智能研究所）
We present GrammarTagger, an open-source grammar profiler which, given an input text, identifies grammatical features useful for language education. The model architecture enables it to learn from a small amount of texts annotated with spans and their labels, which 1) enables easier and more intuitive annotation, 2) supports overlapping spans, and 3) is less prone to error propagation, compared to complex hand-crafted rules defined on constituency/dependency parses. We show that we can bootstrap a grammar profiler model with $F_1 \approx 0.6$ from only a couple hundred sentences both in Englis…
A First Context-Free Grammar Applied to Nawatl Corpora Augmentation
Laboratoire Informatique d’Avignon（阿维尼翁信息实验室）；Avignon Université（阿维尼昂大学）；Facultad de Matemáticas（数学系）；Instituto de Investigaciones en Educación（教育研究所）；Universidad Veracruzana（韦拉克鲁斯大学）
This paper uses the Minimum Description Length paradigm to model the complexity of CxGs (operationalized as the encoding size of a grammar) alongside their descriptive adequacy (operationalized as the encoding size of a corpus given a grammar). These two quantities are combined to measure the quality of potential CxGs against unannotated corpora, supporting discovery-device CxGs for English, Spanish, French, German, and Italian. The results show (i) that these grammars provide significant generalizations as measured using compression and (ii) that more complex CxGs with access to multiple leve…
Brandenburgische Technische Universität Cottbus – Senftenberg（科特布斯-森夫滕堡勃兰登堡工业大学）
Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic slots to interpret the user's intent. In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a \emph{mental lexicon}, comprising syntactic, phonetic and semantic features of the language under considera…
A usage-based Construction Grammar (CxG) posits that slot-constraints generalize from common exemplar constructions. But what is the best model of constraint generalization? This paper evaluates competing frequency-based and association-based models across eight languages using a metric derived from the Minimum Description Length paradigm. The experiments show that association-based models produce better generalizations across all languages by a significant margin.
This study analyses Turkish syntax from an informational point of view. Sign based linguistic representation and principles of HPSG (Head-driven Phrase Structure Grammar) theory are adapted to Turkish. The basic informational elements are nested and inherently sorted feature structures called signs. In the implementation, logic programming tool ALE (Attribute Logic Engine) which is primarily designed for implementing HPSG grammars is used. A type and structure hierarchy of Turkish language is designed. Syntactic phenomena such a s subcategorization, relative clauses, constituent order variatio…
We develop a formal grammatical system called a link grammar, show how English grammar can be encoded in such a system, and give algorithms for efficiently parsing with a link grammar. Although the expressive power of link grammars is equivalent to that of context free grammars, encoding natural language grammars appears to be much easier with the new system. We have written a program for general link parsing and written a link grammar for the English language. The performance of this preliminary system -- both in the breadth of English phenomena that it captures and in the computational resou…
We discuss an extension of the standard logical rules (functional application and abstraction) in Categorial Grammar (CG), in order to deal with some specific cases of polysemy. We borrow from Generative Lexicon theory which proposes the mechanism of {\em coercion}, next to a rich nominal lexical semantic structure called {\em qualia structure}. In a previous paper we introduced coercion into the framework of {\em sign-based} Categorial Grammar and investigated its impact on traditional Fregean compositionality. In this paper we will elaborate on this idea, mostly working towards the introduct…
Einstein Center for Neurosciences Berlin（柏林爱因斯坦神经科学中心）；Technical University Berlin（柏林工业大学）；Imperial College London（帝国理工学院）
Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a sample inefficient exploration phase or lack semantic interpretability. Humans, on the other hand, efficiently detect hierarchical sub-structures induced by their surroundings. It has been argued that this inference process universally applies to language, logical reasoning as well as motor control. Therefore, we propose a cognitive-inspired Reinforcement Learn…
This paper describes our work on parsing Turkish using the lexical-functional grammar formalism. This work represents the first significant effort for parsing Turkish. Our implementation is based on Tomita's parser developed at Carnegie-Mellon University Center for Machine Translation. The grammar covers a substantial subset of Turkish including simple and complex sentences, and deals with a reasonable amount of word order freeness. The complex agglutinative morphology of Turkish lexical structures is handled using a separate two-level morphological analyzer. After a discussion of key relevant…
Translation models based on hierarchical phrase-based statistical machine translation (HSMT) have shown better performances than the non-hierarchical phrase-based counterparts for some language pairs. The standard approach to HSMT learns and apply a synchronous context-free grammar with a single non-terminal. The hypothesis behind the grammar refinement algorithm presented in this work is that this single non-terminal is overloaded, and insufficiently discriminative, and therefore, an adequate split of it into more specialised symbols could lead to improved models. This paper presents a method…
This paper presents a compilation procedure which determines internal and external indices for signs in a unification based grammar to be used in improving the computational efficiency of lexicalist chart generation. The procedure takes as input a grammar and a set of feature paths indicating the position of semantic indices in a sign, and calculates the fixed-point of a set of equations derived from the grammar. The result is a set of independent constraints stating which indices in a sign can be bound to other signs within a complete sentence. Based on these constraints, two tests are formul…
Composing or Not Composing? Towards Distributional Construction Grammars
Laboratoire Parole et Langage, CNRS, France（法国语言与语言实验室，CNRS）；Department of Languages, Literatures and Modern Cultures, University of Bologna, Italy（博洛尼亚大学语言、文学与现代文化系）；Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong（香港理工大学中文与双语研究系）；Department of Philology, Literature, and Linguistics, University of Pisa（比萨大学语言学、文学与语言学系）；ILCB - Institute of Language, Communication and the Brain, France（法国语言、交流与大脑研究所）
We study the adaptation of Link Grammar Parser to the biomedical sublanguage with a focus on domain terms not found in a general parser lexicon. Using two biomedical corpora, we implement and evaluate three approaches to addressing unknown words: automatic lexicon expansion, the use of morphological clues, and disambiguation using a part-of-speech tagger. We evaluate each approach separately for its effect on parsing performance and consider combinations of these approaches. In addition to a 45% increase in parsing efficiency, we find that the best approach, incorporating information from a do…
Ant Group（蚂蚁集团）；Shandong University（山东大学）；Hasso Plattner Institute（哈索·普拉特纳研究所）；University of Potsdam（波茨坦大学）
Recently CKY-based models show great potential in unsupervised grammar induction thanks to their human-like encoding paradigm, which runs recursively and hierarchically, but requires $O(n^3)$ time-complexity. Recursive Transformer based on Differentiable Trees (R2D2) makes it possible to scale to large language model pre-training even with complex tree encoder by introducing a heuristic pruning method. However, the rule-based pruning approach suffers from local optimum and slow inference issues. In this paper, we fix those issues in a unified method. We propose to use a top-down parser as a mo…
CNRS (LIMSI) Université Paris Saclay（法国国家科学研究中心（LIMSI）巴黎萨克雷大学）；Université de Genève CUI（日内瓦大学 CUI）
We present a Sign Language modelling approach allowing to build grammars and create linguistic input for Sign synthesis through avatars. We comment on the type of grammar it allows to build, and observe a resemblance between the resulting expressions and traditional semantic representations. Comparing the ways in which the paradigms are designed, we name and contrast two essentially different strategies for building higher-level linguistic input: "source-and-forward" vs. "target-and-back". We conclude by favouring the latter, acknowledging the power of being able to automatically generate outp…
Quantinuum, Quantum Compositional Intelligence, Oxford（Quantinuum，量子组合智能，牛津）；Oxford University, Department of Computer Science（牛津大学计算机科学系）
This paper concerns the structure of meanings within natural language. Earlier, a framework named DisCoCirc was sketched that (1) is compositional and distributional (a.k.a. vectorial); (2) applies to general text; (3) captures linguistic `connections' between meanings (cf. grammar) (4) updates word meanings as text progresses; (5) structures sentence types; (6) accommodates ambiguity. Here, we realise DisCoCirc for a substantial fragment of English. When passing to DisCoCirc's text circuits, some `grammatical bureaucracy' is eliminated, that is, DisCoCirc displays a significant degree of (7) …
Model structure and complexity selection remains a challenging problem in system identification, especially for parametric non-linear models. Many Evolutionary Algorithm (EA) based methods have been proposed in the literature for estimating model structure and complexity. In most cases, the proposed methods are devised for estimating structure and complexity within a specified model class and hence these methods do not extend to other model structures without significant changes. In this paper, we propose a Tree Adjoining Grammar (TAG) for stochastic parametric models. TAGs can be used to gene…
Lambek Grammars (LG) are a computational modelling of natural language, based on non-commutative compositional types. It has been widely studied, especially for languages where the syntax plays a major role (like English). The goal of this internship report is to demonstrate that every Lambek Grammar can be, not entirely but efficiently, expressed in Abstract Categorial Grammars (ACG). The latter is a novel modelling based on higher-order signature homomorphisms (using $λ$-calculus), aiming at uniting the currently used models. The main idea is to transform the type rewriting system of LGs int…
College of Artificial Intelligence, Nankai University（南开大学人工智能学院）
Grammar error correction (GEC) is an important application aspect of natural language processing techniques. The past decade has witnessed significant progress achieved in GEC for the sake of increasing popularity of machine learning and deep learning, especially in late 2010s when near human-level GEC systems are available. However, there is no prior work focusing on the whole recapitulation of the progress. We present the first survey in GEC for a comprehensive retrospect of the literature in this area. We first give the introduction of five public datasets, data annotation schema, two impor…
