Related papers: Comparing a Linguistic and a Stochastic Tagger
The relationship between communicated language and intended meaning is often probabilistic and sensitive to context. Numerous strategies attempt to estimate such a mapping, often leveraging recursive Bayesian models of communication. In…
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…
With the ever-growing amounts of textual data from a large variety of languages, domains, and genres, it has become standard to evaluate NLP algorithms on multiple datasets in order to ensure consistent performance across heterogeneous…
We introduce a probabilistic framework for quantifying the semantic similarity between two groups of embeddings. We formulate the task of semantic similarity as a model comparison task in which we contrast a generative model which jointly…
Traditional LLM alignment methods are vulnerable to heterogeneity in human preferences. Fitting a na\"ive probabilistic model to pairwise comparison data (say over prompt-completion pairs) yields an inconsistent estimate of the…
Pretraining-based (PT-based) automatic evaluation metrics (e.g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e.g., machine translation and text summarization) due to their better correlation with…
There are several issues with the existing general machine translation or natural language generation evaluation metrics, and question-answering (QA) systems are indifferent in that context. To build robust QA systems, we need the ability…
Many evaluations of large language models (LLMs) in text annotation focus primarily on the correctness of the output, typically comparing model-generated labels to human-annotated ``ground truth'' using standard performance metrics. In…
Latent Semantic Analysis (LSA) is a widely used Information Retrieval method based on "bag-of-words" assumption. However, according to general conception, syntax plays a role in representing meaning of sentences. Thus, enhancing LSA with…
Today's probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the…
Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly. In this paper, we introduce a novel approach to sequence tagging that learns to…
Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing…
We describe the use of energy function optimization in very shallow syntactic parsing. The approach can use linguistic rules and corpus-based statistics, so the strengths of both linguistic and statistical approaches to NLP can be combined…
This paper reports on the recognition component of an intelligent tutoring system that is designed to help foreign language speakers learn standard English. The system models the grammar of the learner, with this instantiation of the system…
Context-Free Grammars (CFGs) and Parsing Expression Grammars (PEGs) have several similarities and a few differences in both their syntax and semantics, but they are usually presented through formalisms that hinder a proper comparison. In…
Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect…
Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long…
How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities…
Machine translation is the process of translating text from one language to another. In this paper, Statistical Machine Translation is done on Assamese and English language by taking their respective parallel corpus. A statistical phrase…
In this paper, we explore the ways to improve POS-tagging using various types of auxiliary losses and different word representations. As a baseline, we utilized a BiLSTM tagger, which is able to achieve state-of-the-art results on the…