Related papers: Tagging French -- comparing a statistical and a co…
This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained…
In this paper we present a Marathi part of speech tagger. It is a morphologically rich language. It is spoken by the native people of Maharashtra. The general approach used for development of tagger is statistical using trigram Method. The…
This paper presents a constraint-based morphological disambiguation approach that is applicable languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological phenomena.…
While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a…
Evaluation metrics are a key ingredient for progress of text generation systems. In recent years, several BERT-based evaluation metrics have been proposed (including BERTScore, MoverScore, BLEURT, etc.) which correlate much better with…
Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser are described. The best resulting system provides roughly as…
Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…
Traditionally linguists have organized languages of the world as language families modelled as trees. In this work we take a contrarian approach and question the tree-based model that is rather restrictive. For example, the affinity that…
Stanford typed dependencies are a widely desired representation of natural language sentences, but parsing is one of the major computational bottlenecks in text analysis systems. In light of the evolving definition of the Stanford…
This thesis presents a constraint-based morphological disambiguation approach that is applicable to languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological…
Several multilingual benchmark datasets have been developed in a semi-automatic manner in the recent past to measure progress and understand the state-of-the-art in the multilingual capabilities of Large Language Models. However, there is…
In this paper, we propose a span labeling approach to model n-gram information for Vietnamese word segmentation, namely SPAN SEG. We compare the span labeling approach with the conditional random field by using encoders with the same…
Traditional language processing tools constrain language designers to specific kinds of grammars. In contrast, model-based language processing tools decouple language design from language processing. These tools allow the occurrence of…
This paper presents a new approach for measuring semantic similarity/distance between words and concepts. It combines a lexical taxonomy structure with corpus statistical information so that the semantic distance between nodes in the…
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates lexical, syntactic, semantic, and structural information…
We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from…
Using more test-time computation during language model inference, such as generating more intermediate thoughts or sampling multiple candidate answers, has proven effective in significantly improving model performance. This paper takes an…
This paper presents various automatic detection methods to extract so called tortured phrases from scientific papers. These tortured phrases, e.g. flag to clamor instead of signal to noise, are the results of paraphrasing tools used to…
Eric Brill introduced transformation-based learning and showed that it can do part-of-speech tagging with fairly high accuracy. The same method can be applied at a higher level of textual interpretation for locating chunks in the tagged…
Comparative constructions play an important role in natural language inference. However, attempts to study semantic representations and logical inferences for comparatives from the computational perspective are not well developed, due to…