Situation recognition is the task of recognizing the activity depictedin an image, including the people and objects involved. Previousmodels for this task typically train a classifier to identify theactivity using a backbone image feature extractor. We propose thatcommonsense knowledge about the objects depicted in an image can alsobe a valuable source of information for activity identification. Previous NLP research has argued that knowledge about the prototypicalfunctions of physical objects is important for language understanding,and NLP techniques have been developed to acquire this knowledge. Our work investigates whether this prototypical function knowledgecan also be beneficial for visual situation recognition. Webuild a framework that incorporates this type of commonsense knowledgein a transformer-based model that is trained to predict the actionverb for situation recognition. Our experimental results show thatadding prototypical function knowledge about physical objects doesimprove performance for the visual activity recognition task.

Commonsense knowledge about the typicalfunctions of physical objects allows people tomake inferences during sentence understanding. For example, we infer that “Sam enjoyedthe book” means that Sam enjoyed reading thebook, even though the action is implicit. Priorresearch has focused on learning the prototypicalfunctions of physical objects in order toenable inferences about implicit actions. Butmany sentences refer to objects even when theyare not used (e.g., “The book fell”). We arguethat NLP systems need to recognize whether anobject is being used before inferring how theobject is used. We define a new task called ObjectUse Classification that determines whethera physical object mentioned in a sentence wasused or likely will be used. We introduce a newdataset for this task and present a classificationmodel that exploits data augmentation methodsand FrameNet when fine-tuning a pre-trainedlanguage model. We also show that object useclassification combined with knowledge aboutthe prototypical functions of objects has thepotential to yield very good inferences aboutimplicit and anticipated actions.

Frame identification is one of the key challenges for frame-semantic parsing. The goal of this task is to determine which frame best captures the meaning of a target word or phrase in a sentence. We present a new model for frame identification that uses a pre-trained transformer model to generate representations for frames and lexical units (senses) using their formal definitions in FrameNet. Our frame identification model assesses the suitability of a frame for a target word in a sentence based on the semantic coherence of their meanings. We evaluate our model on three data sets and show that it consistently achieves better performance than previous systems.

Humans create things for a reason. Ancient people created spears for hunting, knives for cutting meat, pots for preparing food, etc. The prototypical function of a physical artifact is a kind of commonsense knowledge that we rely on to understand natural language. For example, if someone says “She borrowed the book” then you would assume that she intends to read the book, or if someone asks “Can I use your knife?” then you would assume that they need to cut something. In this paper, we introduce a new NLP task of learning the prototypical uses for human-made physical objects. We use frames from FrameNet to represent a set of common functions for objects, and describe a manually annotated data set of physical objects labeled with their prototypical function. We also present experimental results for this task, including BERT-based models that use predictions from masked patterns as well as artifact sense definitions from WordNet and frame definitions from FrameNet.

Prior research has recognized the need to associate affective polarities with events and has produced several techniques and lexical resources for identifying affective events. Our research introduces new classification models to assign affective polarity to event phrases. First, we present a BERT-based model for affective event classification and show that the classifier achieves substantially better performance than a large affective event knowledge base. Second, we present a discourse-enhanced self-training method that iteratively improves the classifier with unlabeled data. The key idea is to exploit event phrases that occur with a coreferent sentiment expression. The discourse-enhanced self-training algorithm iteratively labels new event phrases based on both the classifier’s predictions and the polarities of the event’s coreferent sentiment expressions. Our results show that discourse-enhanced self-training further improves both recall and precision for affective event classification.

People go to different places to engage in activities that reflect their goals. For example, people go to restaurants to eat, libraries to study, and churches to pray. We refer to an activity that represents a common reason why people typically go to a location as a prototypical goal activity (goal-act). Our research aims to learn goal-acts for specific locations using a text corpus and semi-supervised learning. First, we extract activities and locations that co-occur in goal-oriented syntactic patterns. Next, we create an activity profile matrix and apply a semi-supervised label propagation algorithm to iteratively revise the activity strengths for different locations using a small set of labeled data. We show that this approach outperforms several baseline methods when judged against goal-acts identified by human annotators.