Related papers: Tagset Design and Inflected Languages
This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examines the role of…
Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This survey examines why these gaps persist and whether they reflect intrinsic linguistic difficulty…
Several older and more recent results on the boundaries of solvability and unsolvability in tag systems are surveyed. Emphasis will be put on the significance of computer experiments in research on very small tag systems.
Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial…
Word embeddings are a popular way to improve downstream performances in contemporary language modeling. However, the underlying geometric structure of the embedding space is not well understood. We present a series of explorations using…
Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and…
A description of language design choices that have profound effects on software quality, criticism of how ordinary OO languages address them, and explanation of the thinking behind Eiffel's corresponding mechanisms.
This paper proposes a simple test for compositionality (i.e., literal usage) of a word or phrase in a context-specific way. The test is computationally simple, relying on no external resources and only uses a set of trained word vectors.…
Languages differ in terms of the absence or presence of gender features, the number of gender classes and whether and where gender features are explicitly marked. These cross-linguistic differences can lead to ambiguities that are difficult…
Recognizing and categorizing lexical collocations in context is useful for language learning, dictionary compilation and downstream NLP. However, it is a challenging task due to the varying degrees of frozenness lexical collocations…
The goal of this thesis is to advance the exploration of the statistical language learning design space. In pursuit of that goal, the thesis makes two main theoretical contributions: (i) it identifies a new class of designs by specifying an…
This paper describes experiments on identifying the language of a single name in isolation or in a document written in a different language. A new corpus has been compiled and made available, matching names against languages. This corpus is…
Research in emotion analysis is scattered across different label formats (e.g., polarity types, basic emotion categories, and affective dimensions), linguistic levels (word vs. sentence vs. discourse), and, of course, (few well-resourced…
The paper proposes the task of universal semantic tagging---tagging word tokens with language-neutral, semantically informative tags. We argue that the task, with its independent nature, contributes to better semantic analysis for…
A way of extracting French verbal chunks, inflected and infinitive, is explored and tested on effective corpus. Declarative morphological and local grammar rules specifying chunks and some simple contextual structures are used, relying on…
Most modern NLP systems make use of pre-trained contextual representations that attain astonishingly high performance on a variety of tasks. Such high performance should not be possible unless some form of linguistic structure inheres in…
This paper (cmp-lg/yymmnnn) has been accepted for publication in the student session of EACL-95. It outlines ongoing work using statistical and unsupervised neural network methods for clustering words in untagged corpora. Such approaches…
Trigrams'n'Tags (TnT) is an efficient statistical part-of-speech tagger. Contrary to claims found elsewhere in the literature, we argue that a tagger based on Markov models performs at least as well as other current approaches, including…
In derivational morphology, what mechanisms govern the variation in form-meaning relations between words? The answers to this type of questions are typically based on intuition and on observations drawn from limited data, even when a wide…
Concerning different approaches to automatic PoS tagging: EngCG-2, a constraint-based morphological tagger, is compared in a double-blind test with a state-of-the-art statistical tagger on a common disambiguation task using a common tag…