This paper demonstrates that aggregating crowdsourced forecasts benefits from modeling the written justifications provided by forecasters. Our experiments show that the majority and weighted vote baselines are competitive, and that the written justifications are beneficial to call a question throughout its life except in the last quarter. We also conduct an error analysis shedding light into the characteristics that make a justification unreliable.

Negation is underrepresented in existing natural language inference benchmarks. Additionally, one can often ignore the few negations in existing benchmarks and still make the right inference judgments. In this paper, we present a new benchmark for natural language inference in which negation plays a critical role. We also show that state-of-the-art transformers struggle making inference judgments with the new pairs.

When interacting with each other, we motivate, advise, inform, show love or power towards our peers. However, the way we interact may also hold some indication on how successful we are, as people often try to help each other to achieve their goals. We study the chat interactions of thousands of aspiring entrepreneurs who discuss and develop business models. We manually annotate a set of about 5,500 chat interactions with four dimensions of interaction styles (motivation, cooperation, equality, advice). We find that these styles can be reliably predicted, and that the communication styles can be used to predict a number of indices of business success. Our findings indicate that successful communicators are also successful in other domains.

As machine translation (MT) systems progress at a rapid pace, questions of their adequacy linger. In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. We investigate whether translating negation is an issue for modern MT systems using 17 translation directions as test bed. Through thorough analysis, we find that indeed the presence of negation can significantly impact downstream quality, in some cases resulting in quality reductions of more than 60%. We also provide a linguistically motivated analysis that directly explains the majority of our findings. We release our annotations and code to replicate our analysis here: https://github.com/mosharafhossain/negation-mt.

This paper targets the task of determining event outcomes in social media. We work with tweets containing either #cookingFail or #bakingFail, and show that many of the events described in them resulted in something edible. Tweets that contain images are more likely to result in edible albeit imperfect outcomes. Experimental results show that edibility is easier to predict than outcome quality.

Patient adherence is a critical factor in health outcomes. We present a framework to extract adherence information from electronic health records, including both sentence-level information indicating general adherence information (full, partial, none, etc.) and span-level information providing additional information such as adherence type (medication or nonmedication), reasons and outcomes. We annotate and make publicly available a new corpus of 3,000 de-identified sentences, and discuss the language physicians use to document adherence information. We also explore models based on state-of-the-art transformers to automate both tasks.

This paper presents WikiPossessions, a new benchmark corpus for the task of temporally-oriented possession (TOP), or tracking objects as they change hands over time. We annotate Wikipedia articles for 90 different well-known artifacts paintings, diamonds, and archaeological artifacts), producing 799 artifact-possessor relations with associated attributes. For each article, we also produce a full possession timeline. The full version of the task combines straightforward entity-relation extraction with complex temporal reasoning, as well as verification of textual support for the relevant types of knowledge. Specifically, to complete the full TOP task for a given article, a system must do the following: a) identify possessors; b) anchor possessors to times/events; c) identify temporal relations between each temporal anchor and the possession relation it corresponds to; d) assign certainty scores to each possessor and each temporal relation; and e) assemble individual possession events into a global possession timeline. In addition to the corpus, we release evaluation scripts and a baseline model for the task.

In this work we address the processing of negation in Spanish. We first present a machine learning system that processes negation in Spanish. Specifically, we focus on two tasks: i) negation cue detection and ii) scope identification. The corpus used in the experimental framework is the SFU Corpus. The results for cue detection outperform state-of-the-art results, whereas for scope detection this is the first system that performs the task for Spanish. Moreover, we provide a qualitative error analysis aimed at understanding the limitations of the system and showing which negation cues and scopes are straightforward to predict automatically, and which ones are challenging.

This paper introduces two tasks: determining (a) the duration of possession relations and (b) co-possessions, i.e., whether multiple possessors possess a possessee at the same time. We present new annotations on top of corpora annotating possession existence and experimental results. Regarding possession duration, we derive the time spans we work with empirically from annotations indicating lower and upper bounds. Regarding co-possessions, we use a binary label. Cohen’s kappa coefficients indicate substantial agreement, and experimental results show that text is more useful than the image for solving these tasks.

The focus of a negation is the set of tokens intended to be negated, and a key component for revealing affirmative alternatives to negated utterances. In this paper, we experiment with neural networks to predict the focus of negation. Our main novelty is leveraging a scope detector to introduce the scope of negation as an additional input to the network. Experimental results show that doing so obtains the best results to date. Additionally, we perform a detailed error analysis providing insights into the main error categories, and analyze errors depending on whether the model takes into account scope and context information.

Tweets are short messages that often include specialized language such as hashtags and emojis. In this paper, we present a simple strategy to process emojis: replace them with their natural language description and use pretrained word embeddings as normally done with standard words. We show that this strategy is more effective than using pretrained emoji embeddings for tweet classification. Specifically, we obtain new state-of-the-art results in irony detection and sentiment analysis despite our neural network is simpler than previous proposals.

Negation often conveys implicit positive meaning. In this paper, we present a corpus of negations and their underlying positive interpretations. We work with negations from Simple Wikipedia, automatically generate potential positive interpretations, and then collect manual annotations that effectively rewrite the negation in positive terms. This procedure yields positive interpretations for approximately 77% of negations, and the final corpus includes over 5,700 negations and over 5,900 positive interpretations. We also present baseline results using seq2seq neural models.

This paper describes a new dataset and experiments to determine whether authors of tweets possess the objects they tweet about. We work with 5,000 tweets and show that both humans and neural networks benefit from images in addition to text. We also introduce a simple yet effective strategy to incorporate visual information into any neural network beyond weights from pretrained networks. Specifically, we consider the tags identified in an image as an additional textual input, and leverage pretrained word embeddings as usually done with regular text. Experimental results show this novel strategy is beneficial.

This paper presents a corpus and experimental results to extract possession relations over time. We work with Wikipedia articles about artworks, and extract possession relations along with temporal information indicating when these relations are true. The annotation scheme yields many possessors over time for a given artwork, and experimental results show that an LSTM ensemble can automate the task.

This paper presents a set of dimensions to characterize the association between two people. We distinguish between interactions (when somebody refers to somebody in a conversation) and relationships (a sequence of interactions). We work with dialogue scripts from the TV show Friends, and do not impose any restrictions on the interactions and relationships. We introduce and analyze a new corpus, and present experimental results showing that the task can be automated.

This paper presents a corpus and experiments to mine possession relations from text. Specifically, we target alienable and control possessions, and assign temporal anchors indicating when the possession holds between possessor and possessee. We present new annotations for this task, and experimental results using both traditional classifiers and neural networks. Results show that the three subtasks (predicting possession existence, possession type and temporal anchors) can be automated.

This paper presents models to predict event durations. We introduce aspectual features that capture deeper linguistic information than previous work, and experiment with neural networks. Our analysis shows that tense, aspect and temporal structure of the clause provide useful clues, and that an LSTM ensemble captures relevant context around the event.

This paper presents a corpus and experiments to determine dimensions of interpersonal relationships. We define a set of dimensions heavily inspired by work in social science. We create a corpus by retrieving pairs of people, and then annotating dimensions for their relationships. A corpus analysis shows that dimensions can be annotated reliably. Experimental results show that given a pair of people, values to dimensions can be assigned automatically.

This paper describes an approach to determine whether people participate in the events they tweet about. Specifically, we determine whether people are participants in events with respect to the tweet timestamp. We target all events expressed by verbs in tweets, including past, present and events that may occur in the future. We present new annotations using 1,096 event mentions, and experimental results showing that the task is challenging.

This paper presents a framework to understand negation in positive terms. Specifically, we extract positive meaning from negation when the negation cue syntactically modifies a noun or adjective. Our approach is grounded on generating potential positive interpretations automatically, and then scoring them. Experimental results show that interpretations scored high can be reliably identified.

This paper presents a two-step methodology to annotate spatial knowledge on top of OntoNotes semantic roles. First, we manipulate semantic roles to automatically generate potential additional spatial knowledge. Second, we crowdsource annotations with Amazon Mechanical Turk to either validate or discard the potential additional spatial knowledge. The resulting annotations indicate whether entities are or are not located somewhere with a degree of certainty, and temporally anchor this spatial information. Crowdsourcing experiments show that the additional spatial knowledge is ubiquitous and intuitive to humans, and experimental results show that it can be inferred automatically using standard supervised machine learning techniques.

Semantic representation of text is key to text understanding and reasoning. In this paper, we present Polaris, Lymba's semantic parser. Polaris is a supervised semantic parser that given text extracts semantic relations. It extracts relations from a wide variety of lexico-syntactic patterns, including verb-argument structures, noun compounds and others. The output can be provided in several formats: XML, RDF triples, logic forms or plain text, facilitating interoperability with other tools. Polaris is implemented using eight separate modules. Each module is explained and a detailed example of processing using a sample sentence is provided. Overall results using a benchmark are discussed. Per module performance, including errors made and pruned by each module are also analyzed.

This paper presents a supervised method for the detection and extraction of Causal Relations from open domain text. First we give a brief outline of the definition of causation and how it relates to other Semantic Relations, as well as a characterization of their encoding. In this work, we only consider marked and explicit causations. Our approach first identifies the syntactic patterns that may encode a causation, then we use Machine Learning techniques to decide whether or not a pattern instance encodes a causation. We focus on the most productive pattern, a verb phrase followed by a relator and a clause, and its reverse version, a relator followed by a clause and a verb phrase. As relators we consider the words as, after, because and since. We present a set of lexical, syntactic and semantic features for the classification task, their rationale and some examples. The results obtained are discussed and the errors analyzed.