Synthesis Lectures on Human Language Technologies

By Philip Williams, Rico Sennrich, Matt Post, Philipp Koehn. 2016

829 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/990c7e5b74d8a26227f2a135e2a61ec906571691

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Fast and Accurate Dependency Parser using Neural Networks (2014, background): “In recent years, enormous parsing success has been achieved by the use of feature-based discriminative dependency parsers (K¨ubler et al., 2009).”
Learn to Solve Algebra Word Problems Using Quadratic Programming (2015, methodology): “Motivated by the work (Taskar et al., 2005; Li, 2014), we adopt the max-margin objective.”
Higher-Order Explanations of Graph Neural Networks via Relevant Walks (2020, methodology): “For this, we will consider a GCN composed of two interaction layers, to classify sentiments in natural language text [51].”
Aspect Level Sentiment Classification with Deep Memory Network (2016, background): “Aspect level sentiment classiﬁcation is a fundamental task in the ﬁeld of sentiment analysis (Pang and Lee, 2008; Liu, 2012; Pontiki et al., 2014).”
Argumentation Mining on the Web from Information Seeking Perspective (2014, background): “In existing works on argumentation mining of the Web data, the connection is often made to opinion mining (Liu, 2012).”
Survey on Aspect-Level Sentiment Analysis (2016, background): “This field of research, labeled as opinion mining, sentiment analysis, or subjectivity analysis, studies the phenomena of opinion, sentiment, evaluation, appraisal, attitude, and emotion [8].”
Bidirectional LSTM with attention mechanism and convolutional layer for text classification (2019, background): “Especially, the traditional sentiment analysis focuses on identifying the polarity of a text (e.g. positive, negative, neutral) based on the language clues extracted from the textual contents of sentences [7–9] .”
Large Language Models for Information Retrieval: A Survey (2023, neutral): “The term “document” will henceforth refer to any text-based content subject to retrieve, including both long articles and short passages.”
Scene Graph Parsing as Dependency Parsing (2018, background): “The goal of dependency parsing (K¨ubler et al., 2009) is to assign a parent word to every word in a sentence, and every such connection is associated with a label.”
Computational Sociolinguistics: A Survey (2016, background): “The tension between normalizing and preserving the variation in text also arises in the processing and analysis of historical texts (see Piotrowski (2012) for an overview), which also contain many spelling variations.”
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora (2016, background): “Such lexicons are crucial to the growing body of work on NLP analyses of historical text (Piotrowski, 2012) which are informing diachronic linguistics (Hamilton et al., 2016), the digital humanities (Muralidharan and Hearst, 2012), and history (Hendrickx et al., 2011).”
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations (2016, background): “Modern approaches to dependency parsing can be broadly categorized into graph-based and transition-based parsers (Kübler et al., 2008).”
Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach (2014, background): “Sentiment lexicon is crucial for sentiment analysis (or opining mining) as it provides rich sentiment information and forms the foundation of many sentiment analysis systems (Pang and Lee, 2008; Liu, 2012; Feldman, 2013).”
Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets (2016, background): “A core problem of opinion mining or sentiment analysis is to identify each opinion/sentiment target and to classify the opinion/sentiment polarity on the target (Liu, 2012).”
CommonCOW: Massively Huge Web Corpora from CommonCrawl Data and a Method to Distribute them Freely under Restrictive EU Copyright Laws (2016, methodology): “%) are usually not used in the ﬁnal corpus because it does not pass one of the usual quality assessment algorithms or is duplicate material (Schäfer and Bildhauer, 2012; Suchomel and Pomikálek, 2012; Biemann et al., 2013; Schäfer and Bildhauer, 2013; Schäfer et al., 2014 2.”
An Autoencoder Approach to Learning Bilingual Word Representations (2014, background): “For example, high quality POS taggers (Toutanova et al., 2003), parsers (Socher et al., 2013), sentiment analyzers (Liu, 2012) are already available for English but this is not the case for many other languages such as Hindi, Marathi, Bodo, Farsi, Urdu, etc .”
Building Machine Translation Systems for the Next Thousand Languages (2022, methodology): “…Nisaba library of finite-state script normalization and processing utilities (Johny et al., 2021).12 The script operations in Nisaba are efficiently and succinctly represented as weighted finite-state transducers (WFSTs) using Pynini finite-state grammars (Gorman, 2016; Gorman & Sproat, 2021).”