Paper Group NANR 74
Introducing EVALD – Software Applications for Automatic Evaluation of Discourse in Czech. How Well Can We Predict Hypernyms from Word Embeddings? A Dataset-Centric Analysis. Revisiting the ISO standard for dialogue act annotation. Improving NER for Clinical Texts by Ensemble Approach using Segment Representations. May I take your order? A Neural M …
Introducing EVALD – Software Applications for Automatic Evaluation of Discourse in Czech
| Title | Introducing EVALD – Software Applications for Automatic Evaluation of Discourse in Czech |
| Authors | Kate{\v{r}}ina Rysov{'a}, Magdal{'e}na Rysov{'a}, Ji{\v{r}}{'\i} M{'\i}rovsk{'y}, Michal Nov{'a}k |
| Abstract | In the paper, we introduce two software applications for automatic evaluation of coherence in Czech texts called EVALD {–} Evaluator of Discourse. The first one {–} EVALD 1.0 {–} evaluates texts written by native speakers of Czech on a five-step scale commonly used at Czech schools (grade 1 is the best, grade 5 is the worst). The second application is EVALD 1.0 for Foreigners assessing texts by non-native speakers of Czech using six-step scale (A1{–}C2) according to CEFR. Both appli-cations are available online at \url{https://lindat.mff.cuni.cz/services/evald-foreign/}. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1082/ |
| https://doi.org/10.26615/978-954-452-049-6_082 | |
| PWC | https://paperswithcode.com/paper/introducing-evald-a-software-applications-for |
| Repo | |
| Framework | |
How Well Can We Predict Hypernyms from Word Embeddings? A Dataset-Centric Analysis
| Title | How Well Can We Predict Hypernyms from Word Embeddings? A Dataset-Centric Analysis |
| Authors | Ivan Sanchez, Sebastian Riedel |
| Abstract | One key property of word embeddings currently under study is their capacity to encode hypernymy. Previous works have used supervised models to recover hypernymy structures from embeddings. However, the overall results do not clearly show how well we can recover such structures. We conduct the first dataset-centric analysis that shows how only the Baroni dataset provides consistent results. We empirically show that a possible reason for its good performance is its alignment to dimensions specific of hypernymy: generality and similarity |
| Tasks | Natural Language Inference, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2064/ |
| https://www.aclweb.org/anthology/E17-2064 | |
| PWC | https://paperswithcode.com/paper/how-well-can-we-predict-hypernyms-from-word |
| Repo | |
| Framework | |
Revisiting the ISO standard for dialogue act annotation
| Title | Revisiting the ISO standard for dialogue act annotation |
| Authors | Harry Bunt, Volha Petukhova, Alex Chengyu Fang |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7404/ |
| https://www.aclweb.org/anthology/W17-7404 | |
| PWC | https://paperswithcode.com/paper/revisiting-the-iso-standard-for-dialogue-act |
| Repo | |
| Framework | |
Improving NER for Clinical Texts by Ensemble Approach using Segment Representations
| Title | Improving NER for Clinical Texts by Ensemble Approach using Segment Representations |
| Authors | Hamada Nayel, H. L. Shashirekha |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7525/ |
| https://www.aclweb.org/anthology/W17-7525 | |
| PWC | https://paperswithcode.com/paper/improving-ner-for-clinical-texts-by-ensemble |
| Repo | |
| Framework | |
May I take your order? A Neural Model for Extracting Structured Information from Conversations
| Title | May I take your order? A Neural Model for Extracting Structured Information from Conversations |
| Authors | Baolin Peng, Michael Seltzer, Y.C. Ju, Geoffrey Zweig, Kam-Fai Wong |
| Abstract | In this paper we tackle a unique and important problem of extracting a structured order from the conversation a customer has with an order taker at a restaurant. This is motivated by an actual system under development to assist in the order taking process. We develop a sequence-to-sequence model that is able to map from unstructured conversational input to the structured form that is conveyed to the kitchen and appears on the customer receipt. This problem is critically different from other tasks like machine translation where sequence-to-sequence models have been used: the input includes two sides of a conversation; the output is highly structured; and logical manipulations must be performed, for example when the customer changes his mind while ordering. We present a novel sequence-to-sequence model that incorporates a special attention-memory gating mechanism and conversational role markers. The proposed model improves performance over both a phrase-based machine translation approach and a standard sequence-to-sequence model. |
| Tasks | Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1043/ |
| https://www.aclweb.org/anthology/E17-1043 | |
| PWC | https://paperswithcode.com/paper/may-i-take-your-order-a-neural-model-for |
| Repo | |
| Framework | |
Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning
| Title | Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning |
| Authors | Ekaterina Shutova, Lin Sun, Elkin Dar{'\i}o Guti{'e}rrez, Patricia Lichtenstein, Srini Narayanan |
| Abstract | Highly frequent in language and communication, metaphor represents a significant challenge for Natural Language Processing (NLP) applications. Computational work on metaphor has traditionally evolved around the use of hand-coded knowledge, making the systems hard to scale. Recent years have witnessed a rise in statistical approaches to metaphor processing. However, these approaches often require extensive human annotation effort and are predominantly evaluated within a limited domain. In contrast, we experiment with weakly supervised and unsupervised techniques{—}with little or no annotation{—}to generalize higher-level mechanisms of metaphor from distributional properties of concepts. We investigate different levels and types of supervision (learning from linguistic examples vs. learning from a given set of metaphorical mappings vs. learning without annotation) in flat and hierarchical, unconstrained and constrained clustering settings. Our aim is to identify the optimal type of supervision for a learning algorithm that discovers patterns of metaphorical association from text. In order to investigate the scalability and adaptability of our models, we applied them to data in three languages from different language groups{—}English, Spanish, and Russian{—}achieving state-of-the-art results with little supervision. Finally, we demonstrate that statistical methods can facilitate and scale up cross-linguistic research on metaphor. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/J17-1003/ |
| https://www.aclweb.org/anthology/J17-1003 | |
| PWC | https://paperswithcode.com/paper/multilingual-metaphor-processing-experiments |
| Repo | |
| Framework | |
EEG-GRAPH: A Factor-Graph-Based Model for Capturing Spatial, Temporal, and Observational Relationships in Electroencephalograms
| Title | EEG-GRAPH: A Factor-Graph-Based Model for Capturing Spatial, Temporal, and Observational Relationships in Electroencephalograms |
| Authors | Yogatheesan Varatharajah, Min Jin Chong, Krishnakant Saboo, Brent Berry, Benjamin Brinkmann, Gregory Worrell, Ravishankar Iyer |
| Abstract | This paper presents a probabilistic-graphical model that can be used to infer characteristics of instantaneous brain activity by jointly analyzing spatial and temporal dependencies observed in electroencephalograms (EEG). Specifically, we describe a factor-graph-based model with customized factor-functions defined based on domain knowledge, to infer pathologic brain activity with the goal of identifying seizure-generating brain regions in epilepsy patients. We utilize an inference technique based on the graph-cut algorithm to exactly solve graph inference in polynomial time. We validate the model by using clinically collected intracranial EEG data from 29 epilepsy patients to show that the model correctly identifies seizure-generating brain regions. Our results indicate that our model outperforms two conventional approaches used for seizure-onset localization (5-7% better AUC: 0.72, 0.67, 0.65) and that the proposed inference technique provides 3-10% gain in AUC (0.72, 0.62, 0.69) compared to sampling-based alternatives. |
| Tasks | EEG |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7121-eeg-graph-a-factor-graph-based-model-for-capturing-spatial-temporal-and-observational-relationships-in-electroencephalograms |
| http://papers.nips.cc/paper/7121-eeg-graph-a-factor-graph-based-model-for-capturing-spatial-temporal-and-observational-relationships-in-electroencephalograms.pdf | |
| PWC | https://paperswithcode.com/paper/eeg-graph-a-factor-graph-based-model-for |
| Repo | |
| Framework | |
Facebook sentiment: Reactions and Emojis
| Title | Facebook sentiment: Reactions and Emojis |
| Authors | Ye Tian, Thiago Galery, Giulio Dulcinati, Emilia Molimpakis, Chao Sun |
| Abstract | Emojis are used frequently in social media. A widely assumed view is that emojis express the emotional state of the user, which has led to research focusing on the expressiveness of emojis independent from the linguistic context. We argue that emojis and the linguistic texts can modify the meaning of each other. The overall communicated meaning is not a simple sum of the two channels. In order to study the meaning interplay, we need data indicating the overall sentiment of the entire message as well as the sentiment of the emojis stand-alone. We propose that Facebook Reactions are a good data source for such a purpose. FB reactions (e.g. {}Love{''} and {}Angry{''}) indicate the readers{'} overall sentiment, against which we can investigate the types of emojis used the comments under different reaction profiles. We present a data set of 21,000 FB posts (57 million reactions and 8 million comments) from public media pages across four countries. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1102/ |
| https://www.aclweb.org/anthology/W17-1102 | |
| PWC | https://paperswithcode.com/paper/facebook-sentiment-reactions-and-emojis |
| Repo | |
| Framework | |
Exploring an Efficient Handwritten Manipuri Meetei-Mayek Character Recognition Using Gradient Feature Extractor and Cosine Distance Based Multiclass k-Nearest Neighbor Classifier
| Title | Exploring an Efficient Handwritten Manipuri Meetei-Mayek Character Recognition Using Gradient Feature Extractor and Cosine Distance Based Multiclass k-Nearest Neighbor Classifier |
| Authors | Kishorjit Nongmeikapam, Wahengbam Kumar, Mithlesh Prasad Singh |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7541/ |
| https://www.aclweb.org/anthology/W17-7541 | |
| PWC | https://paperswithcode.com/paper/exploring-an-efficient-handwritten-manipuri |
| Repo | |
| Framework | |
When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases
| Title | When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases |
| Authors | Julie Weeds, Thomas Kober, Jeremy Reffin, David Weir |
| Abstract | Non-compositional phrases such as \textit{red herring} and weakly compositionalphrases such as \textit{spelling bee} are an integral part of natural language(Sag, 2002). They are also the phrases that are difficult, or evenimpossible, for good compositional distributional models of semantics.Compositionality detection therefore provides a good testbed for compositionalmethods. We compare an integrated compositional distributional approach, usingsparse high dimensional representations, with the ad-hoc compositional approachof applying simple composition operations to state-of-the-art neuralembeddings. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2085/ |
| https://www.aclweb.org/anthology/E17-2085 | |
| PWC | https://paperswithcode.com/paper/when-a-red-herring-in-not-a-red-herring-using |
| Repo | |
| Framework | |
Applying Multi-Sense Embeddings for German Verbs to Determine Semantic Relatedness and to Detect Non-Literal Language
| Title | Applying Multi-Sense Embeddings for German Verbs to Determine Semantic Relatedness and to Detect Non-Literal Language |
| Authors | Maximilian K{"o}per, Sabine Schulte im Walde |
| Abstract | Up to date, the majority of computational models still determines the semantic relatedness between words (or larger linguistic units) on the type level. In this paper, we compare and extend multi-sense embeddings, in order to model and utilise word senses on the token level. We focus on the challenging class of complex verbs, and evaluate the model variants on various semantic tasks: semantic classification; predicting compositionality; and detecting non-literal language usage. While there is no overall best model, all models significantly outperform a word2vec single-sense skip baseline, thus demonstrating the need to distinguish between word senses in a distributional semantic model. |
| Tasks | Semantic Textual Similarity, Word Embeddings, Word Sense Disambiguation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2086/ |
| https://www.aclweb.org/anthology/E17-2086 | |
| PWC | https://paperswithcode.com/paper/applying-multi-sense-embeddings-for-german |
| Repo | |
| Framework | |
Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus
| Title | Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus |
| Authors | Giulia Donato, Patrizia Paggio |
| Abstract | In this paper we present an annotated corpus created with the aim of analyzing the informative behaviour of emoji {–} an issue of importance for sentiment analysis and natural language processing. The corpus consists of 2475 tweets all containing at least one emoji, which has been annotated using one of the three possible classes: Redundant, Non Redundant, and Non Redundant + POS. We explain how the corpus was collected, describe the annotation procedure and the interface developed for the task. We provide an analysis of the corpus, considering also possible predictive features, discuss the problematic aspects of the annotation, and suggest future improvements. |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5216/ |
| https://www.aclweb.org/anthology/W17-5216 | |
| PWC | https://paperswithcode.com/paper/investigating-redundancy-in-emoji-use-study |
| Repo | |
| Framework | |
Investigating Patient Attitudes Towards the use of Social Media Data to Augment Depression Diagnosis and Treatment: a Qualitative Study
| Title | Investigating Patient Attitudes Towards the use of Social Media Data to Augment Depression Diagnosis and Treatment: a Qualitative Study |
| Authors | Jude Mikal, Samantha Hurst, Mike Conway |
| Abstract | In this paper, we use qualitative research methods to investigate the attitudes of social media users towards the (opt-in) integration of social media data with routine mental health care and diagnosis. Our investigation was based on secondary analysis of a series of five focus groups with Twitter users, including three groups consisting of participants with a self-reported history of depression, and two groups consisting of participants without a self reported history of depression. Our results indicate that, overall, research participants were enthusiastic about the possibility of using social media (in conjunction with automated Natural Language Processing algorithms) for mood tracking under the supervision of a mental health practitioner. However, for at least some participants, there was skepticism related to how well social media represents the mental health of users, and hence its usefulness in the clinical context. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3105/ |
| https://www.aclweb.org/anthology/W17-3105 | |
| PWC | https://paperswithcode.com/paper/investigating-patient-attitudes-towards-the |
| Repo | |
| Framework | |
Proceedings of the Sixth Workshop on Vision and Language
| Title | Proceedings of the Sixth Workshop on Vision and Language |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-2000/ |
| https://www.aclweb.org/anthology/W17-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-sixth-workshop-on-vision |
| Repo | |
| Framework | |
A Calibration Method for Evaluation of Sentiment Analysis
| Title | A Calibration Method for Evaluation of Sentiment Analysis |
| Authors | F.Sharmila Satthar, Roger Evans, Gulden Uchyigit |
| Abstract | Sentiment analysis is the computational task of extracting sentiment from a text document {–} for example whether it expresses a positive, negative or neutral opinion. Various approaches have been introduced in recent years, using a range of different techniques to extract sentiment information from a document. Measuring these methods against a gold standard dataset is a useful way to evaluate such systems. However, different sentiment analysis techniques represent sentiment values in different ways, such as discrete categorical classes or continuous numerical sentiment scores. This creates a challenge for evaluating and comparing such systems; in particular assessing numerical scores against datasets that use fixed classes is difficult, because the numerical outputs have to be mapped onto the ordered classes. This paper proposes a novel calibration technique that uses precision vs. recall curves to set class thresholds to optimize a continuous sentiment analyser{'}s performance against a discrete gold standard dataset. In experiments mapping a continuous score onto a three-class classification of movie reviews, we show that calibration results in a substantial increase in f-score when compared to a non-calibrated mapping. |
| Tasks | Calibration, Information Retrieval, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1084/ |
| https://doi.org/10.26615/978-954-452-049-6_084 | |
| PWC | https://paperswithcode.com/paper/a-calibration-method-for-evaluation-of |
| Repo | |
| Framework | |
