Related papers: MAP Lexicon is useful for segmentation and word di…
Irrelevance-based partial MAPs are useful constructs for domain-independent explanation using belief networks. We look at two definitions for such partial MAPs, and prove important properties that are useful in designing algorithms for…
Induced by "big data," "topic modeling" has become an attractive alternative to mapping co-words in terms of co-occurrences and co-absences using network techniques. Does topic modeling provide an alternative for co-word mapping in research…
Class activation maps are widely used for explaining deep neural networks. Due to its ability to highlight regions of interest, it has evolved in recent years as a key step in weakly supervised learning. A major limitation to the…
The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint…
This paper presents the use of probabilistic class-based lexica for disambiguation in target-word selection. Our method employs minimal but precise contextual information for disambiguation. That is, only information provided by the…
This paper has been withdrawn by the authors due to several major changes in concepts and results. New version will follow briefly as a new e-print.
Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by white space, as well as when dealing with continuous speech…
Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we…
Syllables play an important role in speech synthesis, speech recognition, and spoken document retrieval. A novel, low cost, and language agnostic approach to dividing words into their corresponding syllables is presented. A hybrid genetic…
While recent retrieval techniques do not limit the number of index terms, out-of-vocabulary (OOV) words are crucial in speech recognition. Aiming at retrieving information with spoken queries, we fill the gap between speech recognition and…
A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described. Results of empirical tests showing that the…
Systems now exist which are able to compile unification grammars into language models that can be included in a speech recognizer, but it is so far unclear whether non-trivial linguistically principled grammars can be used for this purpose.…
Is child-directed language (CDL) optimized to support language learning, and which aspects of linguistic development does it facilitate? We investigate this question using neural language models trained on CDL versus adult-directed language…
We present minicons, an open source library that provides a standard API for researchers interested in conducting behavioral and representational analyses of transformer-based language models (LMs). Specifically, minicons enables…
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic…
Large Language Models (LLMs) are poised to play an increasingly important role in our lives, providing assistance across a wide array of tasks. In the geospatial domain, LLMs have demonstrated the ability to answer generic questions, such…
In this paper, we investigate the use of selectional restriction -- the constraints a predicate imposes on its arguments -- in a language model for speech recognition. We use an un-tagged corpus, followed by a public domain tagger and a…
Lexicon acquisition from machine-readable dictionaries and corpora is currently a dynamic field of research, yet it is often not clear how lexical information so acquired can be used, or how it relates to structured meaning representations.…
Semantically-aligned $(speech, image)$ datasets can be used to explore "visually-grounded speech". In a majority of existing investigations, features of an image signal are extracted using neural networks "pre-trained" on other tasks (e.g.,…
Semantic segmentation maps can be used as input to models for maneuvering the controls of a car. However, not all labels may be necessary for making the control decision. One would expect that certain labels such as road lanes or sidewalks…