File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/06/w06-1313_metho.xml
Size: 18,824 bytes
Last Modified: 2025-10-06 14:10:40
<?xml version="1.0" standalone="yes"?> <Paper uid="W06-1313"> <Title>References</Title> <Section position="5" start_page="88" end_page="89" type="metho"> <SectionTitle> 3 Call for Fire Dialogues </SectionTitle> <Paragraph position="0"> Call for Fire procedures are specified in an Army field manual (Army, 2001) with variations based on a unit's standard operating procedure. Messages are brief and followed by confirmations, where any misunderstandings are immediately corrected. A typical CFF is shown in Figure 1.</Paragraph> <Paragraph position="1"> CFFs can generally be divided into three phases. In the first phase (utterances 1-6 in Figure 1) the FOs identify themselves and important information about the CFF, including their coordinates, the kind of fire they are requesting, the location of the target, and the kind of target. In utterance 1 in Figure 1 the FO performs an identification, giving his own call sign and that of the FDC he is calling, and also specifies a method of fire (&quot;adjust fire&quot;) and a method of targeting (&quot;polar&quot;.) Note that when speakers expect a reply, they end their utterance with &quot;over&quot; as in utterance 1, otherwise with &quot;out&quot; as in the confirmation in utterance 2. In utterance 3 the FO gives target coordinates, and in utterance 5 the FO identifies the target as a BMP (a type of light tank) and requests ICM rounds (&quot;improved conventional munitions&quot;.) These turns typically follow one another in quick sequence.</Paragraph> <Paragraph position="2"> In the second phase of a CFF, (utterances 7-12 in Figure 1), after the FDC decides what kind of fire they will send, they inform the FO in a message to observer (MTO) as in utterance 7. This includes the units that will fire (&quot;kilo alpha&quot;), the kind of ammunition (&quot;high explosive&quot;), the number of rounds and method of fire (&quot;4 rounds adjust fire&quot;), and the target number (&quot;alpha bravo one zero zero zero&quot;). CFFs are requests rather than orders, and they may be denied in full or in part. In this example, the FO's request for ICM rounds was denied in favor of High Explosive rounds. Next the FDC informs the FO when the fire mission has been shot, as in utterance 9, and when the fire is about to land, as in utterance 11. Each of these are confirmed by the FO.</Paragraph> <Paragraph position="3"> In the third phase, (utterances 13-20 in Figure 1) the FO regains dialogue initiative. Depending on the observed results, the FO may request that the fire be repeated with an adjust in location or method of fire. In utterance 13 the FO requests that the shot be re-sent to a location 50 meters to the right of the previous shot as a &quot;fire for effect&quot; all-out bombardment rather than an &quot;adjust fire&quot; targeting fire. This is followed by the abbreviated FDC-initiated phase of utterances 15-18. In utterance 19 the FO ends the mission, describing the results and number of casualties.</Paragraph> <Paragraph position="4"> Besides the behavior shown, at any turn either participant may request or initiate an intelligence report or request the status of a mission. Furthermore, after receiving an MTO the FO may immediately begin another fire mission and thus have multiple missions active; subsequent adjusts are disambiguated with the target numbers assigned during the MTOs.</Paragraph> </Section> <Section position="6" start_page="89" end_page="93" type="metho"> <SectionTitle> 4 Dialogue Manager </SectionTitle> <Paragraph position="0"> We have constructed an Information State-based dialogue manager (Larsson and Traum, 2000) on this domain consisting of a set of dialogue moves, a set of informational components with appropriate formal representations, and a set of update rules with an update strategy. We describe each of these in turn.</Paragraph> <Section position="1" start_page="89" end_page="89" type="sub_section"> <SectionTitle> 4.1 Dialogue Moves </SectionTitle> <Paragraph position="0"> We defined a set of dialogue moves to represent the incoming FO utterances based on a study of transcripts of human-controlled JFETS-UTM sessions, Army manuals, and the needs of the simulator. As shown in Figure 2 these are divided into three groups: those that provide information about the FO or the fire mission, those that confirm information that the FDC has transmitted, and those that make requests.</Paragraph> <Paragraph position="1"> The dialogue moves that provide information include those in which the FOs transmit their Observer Coordinates (grid location on a map), a generic Situation Report, or one of the various components of a fire mission request ranging from call sign Identification to final End of Mission. The dialogue moves that confirm information include those that confirm the MTO and other FDC-initiated utterances, or a general report on scenario Intel. The final group includes requests to check radio functionality, to repeat the previous utterance, for status of a shot, to stand by for transmission of information, and finally a set of commands such as &quot;check fire&quot; requesting cancellation of a submitted fire mission.</Paragraph> <Paragraph position="2"> Each of these dialogue moves contains information important to the dialogue manager. This information is captured by the parameters of the dialogue move, which are enumerated in Figure 3.</Paragraph> <Paragraph position="3"> Each parameter is listed with the dialogue move it usually occurs with, but this assignment is not strict. For example, &quot;number of enemies&quot; param- null eters representing the call signs of the FDC and the FO, and the Warning Order has two parameters representing the method of fire and method of location. Parameters need to be identified to confirm back to the FO, and in some cases to be sent to the simulator and for use in updating the information state. In the example in Figure 4, the fact that the requested method of fire is an &quot;adjust fire&quot; will be sent to the simulator, and the fact that a method of fire has been given will be updated in the information state.</Paragraph> <Paragraph position="4"> Identification: steel one nine this is gator niner one fdc id: steel one nine fo id: gator niner one Warning Order: adjust fire polar method of fire: adjust fire</Paragraph> </Section> <Section position="2" start_page="89" end_page="92" type="sub_section"> <SectionTitle> 4.2 Informational Components </SectionTitle> <Paragraph position="0"> The Radiobot-CFF dialogue manager's information state consists of five classes of informational components, defined by their role in the dialogue and their level of accessibility to the user.</Paragraph> <Paragraph position="1"> These are the Fire Mission Decision components, the Fire Mission Value components, the Post-Fire Value components, the Disambiguation components, and the Update Rule Processing components. null By dividing the components into multiple classes we separate those that are simulator-specific from more general aspects of the domain. Decisions to fire are based on general constraints of the domain, whereas the exact components to include in a message to simulator will be simulator-specific. Also, the components have been designed such that there is almost no overlap in the update rules that modify them (see section 4.3). This reduces the complexity involved in editing or adding rules; although there are over 100 rules in the information state, there are few unanticipated side-effects when rules are altered.</Paragraph> <Paragraph position="2"> The first class of components are the Fire Mission Decision components, which are used to determine whether enough information has been collected to send fire. These components are boolean flags, updated by rules based on incoming dialogue moves and parameters. Figure 5 shows the values of these components after utterance 3 in Figure 1 has been processed. The FO has given a warning order, and a target location (which can either be given through a grid location, or through a combination of direction and distance values, and observer coordinates), so the appropriate components are &quot;true&quot;. After the FO gives a target description, that component will be true as well, and an update rule will recognize that enough information has been gathered to send a fire mission.</Paragraph> <Paragraph position="3"> has warning order? true has target location? true has grid location? false has polar direction? true has polar distance? true has polar obco? true has target descr? false The second class of information state components is the set of Fire Mission Value components, which track the value of various information el- null ements necessary for requesting a fire mission.</Paragraph> <Paragraph position="4"> These are specific to the FireSim XXI simulator. Figure 6 shows the values after utterance 3 in Figure 1. Components such as &quot;direction value&quot; take number values, and components such as &quot;method of fire&quot; take values from a finite set of possibilities. Several of these components, such as &quot;attitude&quot; have defaults that are rarely changed. Once the dialogue manager or human trainer decides that it has enough information to request fire, these components are translated into a simulator command and sent to the simulator.</Paragraph> <Paragraph position="5"> method of control: adjust fire method of fire: adjust fire method of engagement: none given modifiable by the trainer. Figure 7 shows the GUI which the trainer can use to take control of the session, edit any of the Fire Mission Value components, and relinquish control of the session back to Radiobot-CFF. This allows the trainer to correct any mistakes that the Radiobot may have made or test the trainee's adaptability by sending the fire to an unexpected location. The example shown in dialogue manager has decided that it has enough information to send a fire. The trainer may send the message or edit it and then send it. A second GUI, not shown, allows the trainer to take control of the outgoing speech of the Radiobot, and, in semi-automated mode, either confirm the sending of a suggested output utterance, alter it before sending, or author new text for the radiobot to say. The third class of components is the Post-Fire Value components, which are also exposed to the trainer for modification. The example shown in Figure 8 is from after utterance 13 in Figure 1; the FO has requested an &quot;adjust fire&quot; with an indicator of &quot;fire for effect&quot; and a right adjustment of 50. At this point in the dialogue the FO could have instead chosen to end the mission. If the initial fire had been a &quot;fire for effect&quot; it could have been re- null peated, rather than following up an initial &quot;adjust fire.&quot; The adjust fire stage does not have any decision components because typically the adjust information is given in one move.</Paragraph> <Paragraph position="6"> adjust fire: true shift indicator: fire for effect The fourth class, Disambiguation components, are used by many rules to disambiguate local information based on global dialogue features. The example shown in Figure 9 is from the dialogue in Figure 1, after utterance 1. The &quot;mission is polar&quot; component helps determine the method of target location if speech recognition erroneously detects both polar and grid coordinates. Target numbers allow the FOs to handle multiple missions at the same time (e.g., starting a new call for fire, before the previous mission has been completed). The &quot;missions active&quot; component tracks how many missions are currently being discussed.</Paragraph> <Paragraph position="7"> The &quot;phase&quot; refers to the state of a three-state FSA that tracks which of the three subdialogue phases (described in section 3) the dialogue is in for the most recently-discussed mission.</Paragraph> <Paragraph position="8"> An example of the use of the Disambiguation components is to determine whether the phrase &quot;fire for effect&quot; refers to an adjustment of a previous mission or the initiation of a new mission. In utterance 13 in Figure 1, &quot;fire for effect&quot; refers to an adjustment of a CFF that began with an &quot;adjust fire&quot; in utterance 1. However, the FO could have started that CFF by calling for a &quot;fire for effect&quot;. Furthermore the FO could have started a second CFF in utterance 13 rather than doing an adjust, and might have specified &quot;fire for effect&quot;. By using a rule to check the phase of the mission the move can be disambiguated to understand that it is referring to an adjustment, rather than the initiation of a new fire mission.</Paragraph> <Paragraph position="9"> mission is polar?: true target number: 0 missions active: 0 last method of fire: adjust phase: Info-Gathering The last class of components, shown in Figure 10, is closely tied to the update rule processing, and is therefore described in the following section. current reply: gator nine one this is steel one nine previous reply: understood? true send EOM? false send repeat? false send repeat adjust? false send repeat ffe? false Figure 10: Update Rule Processing Components</Paragraph> </Section> <Section position="3" start_page="92" end_page="93" type="sub_section"> <SectionTitle> 4.3 Update Rules </SectionTitle> <Paragraph position="0"> Update rules update the informational components, build a message to send to the FO, build a message to send to the simulator, and decide whether a message should actually be sent to the FO or simulator.</Paragraph> <Paragraph position="1"> As an example of rule application, consider the processing of utterance 1 in Figure 1. Figure 4 shows the moves and parameters for this utterance. When the dialogue manager processes this utterance, a set of rules associated with the Identification move are applied, which starts building a response to the FO. This response is built in the &quot;current reply&quot; Update Rule Processing component. Figure 10 shows a reply in the process of being built: a rule has recognized that an Identification move is being given, and has filled in slots in a template with the necessary information and added it to the &quot;current reply&quot; component.</Paragraph> <Paragraph position="2"> Next, the update rules will recognize that a Warning Order is being given, and will identify that it is an &quot;adjust fire&quot; method of fire, and update the &quot;has warning order&quot; decision component, the &quot;method of control&quot; and &quot;method of fire&quot; value components, and the &quot;last method of fire&quot; disambiguation component. As part of this, the appropriate fields of the GUIs will be filled in to allow the trainer to override the FO's request if need be.</Paragraph> <Paragraph position="3"> Another rule will then fill in the slots of a template to add &quot;adjust fire polar&quot; to the current reply, and later another rule will add &quot;out&quot;, thus finishing the reply to the FO. After the reply is finished, it will place it in the &quot;previous reply&quot; component, for reference if the FO requests a repeat of the previous utterance.</Paragraph> <Paragraph position="4"> Certain rules are specified as achieving comprehension -- that is, if they are applied, the &quot;understood&quot; variable for that turn is set. If no reply has been built but the move has been understood, then no reply needs to be sent. This happens, for example, for each of utterances 8, 10, and 12 in Figure 1: because they are confirmations of utterances that the FDC has initiated, they do not need to be replied to. Similarly, no reply needs to be sent if no reply has been built and the incoming message is empty or only contains one or two words indicative of an open mic and background noise. Finally, if no reply has been built and the move has not been understood, then the FO is prompted to repeat the message.</Paragraph> <Paragraph position="5"> As described above, the Fire Mission Decision components are used to determine whether to send a fire mission. For other communications with the simulator, a simpler approach is possible. The decisions to send an end of mission, a repeat fire, or a repeat fire with the 'adjust' or 'fire for effect' specification can be made with update rules acting on a single boolean, and so these are also part of the or more dialogue moves, each with a set of rules specific to it. The dialogue manager applies the appropriate rules to each dialogue move in the utterance before applying the rules that send the FO messages or simulator commands, as shown in Figure 11. Rules for producing replies and simulator commands are delayed until the end of processing an utterance to allow for utterances that may contain self-corrections or relevant details later in the turn.</Paragraph> <Paragraph position="6"> for each dialogue move in utterance apply rules for that dialogue move end for apply rules to send reply to FO apply rules to send simulator commands</Paragraph> </Section> </Section> <Section position="7" start_page="93" end_page="93" type="metho"> <SectionTitle> 5 Error Handling </SectionTitle> <Paragraph position="0"> Radiobot-CFF is able to handle various kind of problematic input in a number of ways. It can handle partially correct information, as in Figure 12.</Paragraph> <Paragraph position="1"> Speech recognition errors caused the &quot;three casualties&quot; information to be lost, but the update rules were able to handle the essential part of the FO contribution: that the mission was ended, and that the target was neutralized. The domain is forgiving in this particular example, although a strict trainer might want to intervene by the GUI and insist that the FO re-submit the end of mission report. null FO Said: end of mission target neutralized estimate three casualties over ASR Output: in end of mission target neutralized as the make three catch a these over Radiobot: end of mission target neutralized out In other cases, such as when giving number coordinates, all information must be fully grounded. An example of this is in Figure 13, where the number &quot;five&quot; is lost by the speech recognition. In this case, the domain-appropriate response is to prompt for a repetition.</Paragraph> <Paragraph position="2"> FO Said: right five zero over ASR Output: right by zero over</Paragraph> </Section> class="xml-element"></Paper>