We analyze some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system. In particular, we address issues such as the representation of text chunks, the inference approach needed to combine local NER decisions, the sources of prior knowledge and how to use them within an NER system. In the process of comparing several solutions to these challenges we reach some surprising conclusions, as well as develop an NER system that achieves 90.8 F1 score on the CoNLL-2003 NER shared task, the best reported result for this dataset.

/pdf/design-challenges-and-misconceptions-in-named-entity-1p7hh240x5.pdf

Design Challenges and Misconceptions in Named Entity Recognition

This introductory text to statistical machine translation (SMT) provides all of the theories and methods needed to build a statistical machine translator, such as Google Language Tools and Babelfish. In general, statistical techniques allow automatic translation systems to be built quickly for any language-pair using only translated texts and generic software. With increasing globalization, statistical machine translation will be central to communication and commerce. Based on courses and tutorials, and classroom-tested globally, it is ideal for instruction or self-study, for advanced undergraduates and graduate students in computer science and/or computational linguistics, and researchers in natural language processing. The companion website provides open-source corpora and tool-kits.

/pdf/statistical-machine-translation-1yr1jtzcjp.pdf

Statistical Machine Translation

We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters are estimated in polynomial time using an EM algorithm. The model produces word alignments that are better than those produced by IBM Model 5.

https://faculty.washington.edu/fxia/courses/LING580MT/yamada_2001.pdf

A Syntax-based Statistical Translation Model

We describe the CoNLL-2000 shared task: dividing text into syntactically related non-overlapping groups of words, so-called text chunking. We give background information on the data sets, present a general overview of the systems that have taken part in the shared task and briefly discuss their performance.

Introduction to the CoNLL-2000 shared task: chunking

We describe a state-of-the-art sentiment analysis system that detects (a) the sentiment of short informal textual messages such as tweets and SMS (message-level task) and (b) the sentiment of a word or a phrase within a message (term-level task). The system is based on a supervised statistical text classification approach leveraging a variety of surface-form, semantic, and sentiment features. The sentiment features are primarily derived from novel high-coverage tweet-specific sentiment lexicons. These lexicons are automatically generated from tweets with sentiment-word hashtags and from tweets with emoticons. To adequately capture the sentiment of words in negated contexts, a separate sentiment lexicon is generated for negated words.

The system ranked first in the SemEval-2013 shared task 'Sentiment Analysis in Twitter' (Task 2), obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. Post-competition improvements boost the performance to an F-score of 70.45 (message-level task) and 89.50 (term-level task). The system also obtains state-of-the-art performance on two additional datasets: the SemEval-2013 SMS test set and a corpus of movie review excerpts. The ablation experiments demonstrate that the use of the automatically generated lexicons results in performance gains of up to 6.5 absolute percentage points.

/pdf/sentiment-analysis-of-short-informal-texts-4lbmfxinxh.pdf

Sentiment analysis of short informal texts

We present a unified technique to solve different shallow parsing tasks as a tagging problem using a Hidden Markov Model-based approach (HMM). This technique consists of the incorporation of the relevant information for each task into the models. To do this, the training corpus is transformed to take into account this information. In this way, no change is necessary for either the training or tagging process, so it allows for the use of a standard HMM approach. Taking into account this information, we construct a Specialized HMM which gives more complete contextual models. We have tested our system on chunking and clause identification tasks using different specialization criteria. The results obtained are in line with the results reported for most of the relevant state-of-the-art approaches.

/pdf/shallow-parsing-using-specialized-hmms-10pp1t8v9t.pdf

Shallow parsing using specialized hmms

This paper describes an approach for political tendency identification of Twitter users. We define some metrics that take into account the polarity of the political entities in the tweets of each user. To obtain this polarities we present the sentiment analysis system developed. The evaluation was performed on the general corpus developed at TASS2013 workshop for Spanish. To our knowledge, the results obtained for the sentiment analysis task and the political tendency identification task are the best results published until now using this data set.

Political Tendency Identification in Twitter using Sentiment Analysis Techniques

In this paper we present an integrated system for tagging and chunking texts from a certain language. The approach is based on stochastic finite-state models that are learnt automatically. This includes biagram models or finite-state automata learnt using grammatical inference techniques. As the models involved in our system are learnt automatically, this is a very flexible and portable system.In order to show the viability of our approach we present results for tagging and chunking using bigram models on the Wall Street Journal corpus. We have achieved an accuracy rate for tagging of 96.8%, and a precision rate for NP chunks of 94.6% with a recall rate of 93.6%.

/pdf/tagging-and-chunking-with-bigrams-59m8huwc8z.pdf

Tagging and chunking with bigrams

This work has been partially supported by the Spanish Ministerio de Ciencia, Innovacion y Universidades and FEDER founds under project AMIC (TIN2017-85854-C4-2-R) and the GiSPRO project (PROMETEU/2018/176). Work of Jose-Angel Gonzalez is financed by Universitat Politecnica de Valencia under grant PAID-01-17.

Transformer based contextualization of pre-trained word embeddings for irony detection in Twitter

We introduce a simple method to build Lexicalized Hidden Markov Models (L-HMMs) for improving the precision of part-of-speech tagging. This technique enriches the contextual Language Model taking into account a set of selected words empirically obtained. The evaluation was conducted with different lexicalization criteria on the Penn Treebank corpus using the TnT tagger. This lexicalization obtained about a 6% reduction of the tagging error, on an unseen data test, without reducing the efficiency of the system. We have also studied how the use of linguistic resources, such as dictionaries and morphological analyzers, improves the tagging performance. Furthermore, we have conducted an exhaustive experimental comparison that shows that Lexicalized HMMs yield results which are better than or similar to other state-of-the-art part-of-speech tagging approaches. Finally, we have applied Lexicalized HMMs to the Spanish corpus LexEsp.

Ferran Pla

Papers

Shallow parsing using specialized hmms

Political Tendency Identification in Twitter using Sentiment Analysis Techniques

Tagging and chunking with bigrams

Transformer based contextualization of pre-trained word embeddings for irony detection in Twitter

Improving part-of-speech tagging using lexicalized HMMs